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

    Neuronpedia

    INDEX
    Explanations

    references to political nominations

    oai_token-act-pair · gpt-3.5-turbo

    references to political nominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijk
    -0.75
     Bulg
    -0.71
    Ku
    -0.70
    gm
    -0.68
    working
    -0.68
    BC
    -0.67
    birth
    -0.66
    Basic
    -0.63
    reth
    -0.62
     Extrem
    -0.62
    POSITIVE LOGITS
     nomination
    0.93
     nominate
    0.92
     nominees
    0.89
    eering
    0.89
     nominating
    0.88
     nominations
    0.85
     candidate
    0.83
     nominated
    0.83
    eers
    0.81
    cand
    0.81
    Act Density 0.032%

    No Known Activations