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

    Neuronpedia

    INDEX
    Explanations

    names of prominent political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vity
    -0.68
    notes
    -0.65
     wonders
    -0.65
    Reviewer
    -0.61
     Kru
    -0.61
    dri
    -0.60
    hiro
    -0.59
    fu
    -0.58
    ãĤŃ
    -0.58
    edit
    -0.57
    POSITIVE LOGITS
     whom
    0.80
     TAMADRA
    0.73
     Jr
    0.71
     imperson
    0.68
    arella
    0.67
     III
    0.64
    enstein
    0.62
    bey
    0.61
    ovich
    0.59
    Jr
    0.59
    Act Density 0.171%

    No Known Activations