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

    Neuronpedia

    INDEX
    Explanations

    names of prestigious halls of fame

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hall of Fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.79
    resp
    -0.73
    cos
    -0.73
    microsoft
    -0.73
    alam
    -0.72
    abre
    -0.68
    onal
    -0.67
    owicz
    -0.66
    wise
    -0.65
    apest
    -0.65
    POSITIVE LOGITS
     Fame
    1.05
    brance
    0.87
     induction
    0.86
     honors
    0.86
     plaque
    0.82
     Bowl
    0.79
     Trophy
    0.78
    spective
    0.74
     induct
    0.72
     trustee
    0.72
    Act Density 0.016%

    No Known Activations