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

    Neuronpedia

    INDEX
    Explanations

    strings related to application names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.74
    shots
    -0.70
    emaker
    -0.67
    pei
    -0.66
    manship
    -0.65
    culus
    -0.64
    ew
    -0.63
    jay
    -0.63
    states
    -0.63
     bullet
    -0.63
    POSITIVE LOGITS
    ained
    1.14
    ainer
    1.10
    ategy
    1.10
    uments
    1.01
    aining
    0.98
    ategic
    0.97
    ains
    0.95
    anded
    0.94
    ader
    0.91
    icken
    0.90
    Act Density 0.024%

    No Known Activations