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

    Neuronpedia

    INDEX
    Explanations

    references to liberation or freedom

    oai_token-act-pair · gpt-3.5-turbo

    words related to freedom and liberation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDER
    -0.67
    iop
    -0.66
     frown
    -0.59
     deterrent
    -0.58
     approximation
    -0.57
     Humph
    -0.57
     nose
    -0.57
     antip
    -0.56
     bacter
    -0.56
     occurrence
    -0.55
    POSITIVE LOGITS
    bies
    0.94
    ktop
    0.91
    chwitz
    0.89
    oise
    0.83
    ãĥķãĤ¡
    0.83
    ãĥ¯
    0.82
    zie
    0.80
    stretched
    0.77
    irs
    0.76
     slaves
    0.76
    Act Density 0.057%

    No Known Activations