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

    Neuronpedia

    INDEX
    Explanations

    words related to achievements, awards, recognition, and success

    oai_token-act-pair · gpt-3.5-turbo

    accolades and achievements related to fame and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addons
    -0.88
    onics
    -0.74
     contingency
    -0.73
     contrace
    -0.73
    atics
    -0.72
    rians
    -0.71
    vous
    -0.69
    nea
    -0.64
    axis
    -0.64
     Fork
    -0.62
    POSITIVE LOGITS
     fame
    1.78
     accol
    1.76
     notoriety
    1.68
     acclaim
    1.65
     renown
    1.48
     awards
    1.44
     popularity
    1.36
     endorsements
    1.31
     reputation
    1.29
     honors
    1.28
    Act Density 1.014%

    No Known Activations