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

    Neuronpedia

    INDEX
    Explanations

    special characters

    oai_token-act-pair · gpt-3.5-turbo

    statements about significant events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.63
    aditional
    -0.60
     precaution
    -0.60
    boro
    -0.60
     unemploy
    -0.59
     ceremonial
    -0.58
     tremend
    -0.58
     favourite
    -0.58
     squats
    -0.58
     civilisation
    -0.58
    POSITIVE LOGITS
    âĢ
    1.17
    ̶
    1.11
    ³³³³
    1.10
    ãĢ
    1.05
    ³³³
    1.01
    ³³³³³³³³
    0.98
    âĢł
    0.96
    îĢ
    0.96
    */
    0.95
    âĹı
    0.95
    Act Density 0.543%

    No Known Activations