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

    Neuronpedia

    INDEX
    Explanations

    references to controversial or unusual behavior and events involving animals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     notor
    -0.99
     mef
    -0.95
     permu
    -0.93
     gend
    -0.92
     anse
    -0.89
     utop
    -0.88
     hoj
    -0.88
     doman
    -0.87
     palab
    -0.87
     franz
    -0.86
    POSITIVE LOGITS
     always
    0.70
     was
    0.68
     occasionally
    0.67
     depended
    0.65
     knew
    0.65
     never
    0.65
     thrived
    0.65
     wasn
    0.64
     kept
    0.62
     sometimes
    0.61
    Act Density 0.723%

    No Known Activations