Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific names or terms such as "Joe", "John", or "Camelot" in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names and brands associated with products and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.10
    3:0.04
    4:0.18
    5:0.03
    6:0.04
    7:0.11
    8:0.04
    9:0.06
    10:0.18
    11:0.11
    Negative Logits
    #$#$
    -1.12
    tumblr
    -0.97
    alias
    -0.95
    nu
    -0.93
    photos
    -0.92
    team
    -0.92
    nai
    -0.91
    etheless
    -0.90
    charges
    -0.87
    grand
    -0.86
    POSITIVE LOGITS
     Execution
    1.09
    Tube
    0.99
     Enterprise
    0.96
    Pacific
    0.93
     Federation
    0.91
     Interactive
    0.91
    Runtime
    0.89
    Assembly
    0.87
     Evangel
    0.86
    Arcade
    0.86
    Act Density 0.759%

    No Known Activations