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

    Neuronpedia

    INDEX
    Explanations

    negative events or controversial topics related to society or individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with negative events, issues, or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.66
    yss
    -0.66
    EngineDebug
    -0.63
    oÄŁ
    -0.63
    oux
    -0.62
    same
    -0.60
    isma
    -0.58
    odore
    -0.57
    erity
    -0.57
     Was
    -0.56
    POSITIVE LOGITS
     imaginable
    1.30
     involving
    0.96
    mith
    0.92
    hooting
    0.92
    paces
    0.87
     occurring
    0.83
     plag
    0.82
    hips
    0.81
     pertaining
    0.80
     happening
    0.79
    Act Density 0.371%

    No Known Activations