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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal ownership or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to individual autonomy or self-sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olic
    -0.73
    mes
    -0.72
    obar
    -0.69
    recated
    -0.68
    alez
    -0.68
    wark
    -0.67
    onal
    -0.66
    gres
    -0.65
    Grade
    -0.63
    ————————
    -0.63
    POSITIVE LOGITS
     accord
    1.16
     backyard
    0.91
     merits
    0.85
     vol
    0.84
     dime
    0.83
     admission
    0.80
     vomit
    0.80
     initiative
    0.79
     merit
    0.77
     creations
    0.76
    Act Density 0.056%

    No Known Activations