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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal intent

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.78
    cit
    -0.76
    visors
    -0.72
     Tycoon
    -0.68
    mint
    -0.63
    java
    -0.62
     Solitaire
    -0.62
     beds
    -0.62
     Temper
    -0.61
    journal
    -0.61
    POSITIVE LOGITS
    ality
    1.12
    ful
    0.95
    fulness
    0.93
    edly
    0.92
    ually
    0.92
    lessly
    0.88
    ual
    0.86
     intent
    0.83
    uality
    0.79
     deceive
    0.78
    Act Density 0.029%

    No Known Activations