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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "what"

    oai_token-act-pair · gpt-3.5-turbo

    questions or statements beginning with "what"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tornado
    -0.58
    Ħ¢
    -0.57
    ograph
    -0.57
    piece
    -0.56
    ISION
    -0.55
     dred
    -0.55
    por
    -0.55
    enberg
    -0.54
     Panc
    -0.53
    Ļ½
    -0.53
    POSITIVE LOGITS
     transpired
    0.91
     happened
    0.91
    Downloadha
    0.90
     happens
    0.86
     constitutes
    0.85
    andestine
    0.83
     amounts
    0.81
     constituted
    0.81
    ?),
    0.79
    soever
    0.79
    Act Density 0.044%

    No Known Activations