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

    Neuronpedia

    INDEX
    Explanations

    references to candidates in a political or electoral context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tw
    -0.70
     Gew
    -0.64
    Skocz
    -0.61
     cha
    -0.58
    dw
    -0.57
     dw
    -0.57
    ج
    -0.57
    th
    -0.56
    心
    -0.56
    w
    -0.55
    POSITIVE LOGITS
     candidates
    2.13
     Candidates
    1.99
     candidate
    1.91
    candidates
    1.90
    Candidates
    1.82
     Candidate
    1.82
    Candidate
    1.79
     CANDIDATE
    1.77
    candidate
    1.73
     kandid
    1.57
    Act Density 0.098%

    No Known Activations