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

    Neuronpedia

    INDEX
    Explanations

    actions related to violent events

    oai_token-act-pair · gpt-3.5-turbo

    violent actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibrary
    -0.73
     Founders
    -0.63
    erala
    -0.62
    urers
    -0.60
     nowadays
    -0.60
     Historically
    -0.59
    terday
    -0.58
     Founding
    -0.57
    quartered
    -0.57
     historically
    -0.56
    POSITIVE LOGITS
    livion
    0.69
     unsuspecting
    0.68
    ))))
    0.68
    VERTISEMENT
    0.66
    EXT
    0.64
    zzle
    0.64
     blinding
    0.63
    )))
    0.60
    eming
    0.60
    ggle
    0.59
    Act Density 1.056%

    No Known Activations