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

    Neuronpedia

    INDEX
    Explanations

    words related to surprises, shocks, or unexpected events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.55
     الحره
    -0.51
    djangoproject
    -0.48
    ➕
    -0.47
    Pautan
    -0.47
    resta
    -0.45
    apist
    -0.45
     Brett
    -0.45
     Teb
    -0.44
    Mull
    -0.44
    POSITIVE LOGITS
     shock
    1.39
     Shock
    1.25
     SHOCK
    1.20
    shock
    1.19
     shocks
    1.17
    Shock
    1.12
     shocked
    1.06
    shocked
    1.02
     fuper
    0.92
     whofe
    0.91
    Act Density 0.060%

    No Known Activations