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

    Neuronpedia

    INDEX
    Explanations

    members of groups or collectives

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cca
    -0.63
    livion
    -0.62
     Athletic
    -0.59
     Beginning
    -0.59
     confidence
    -0.58
     sorts
    -0.57
     Greens
    -0.57
    ////////////////////////////////
    -0.56
     Assets
    -0.56
    ãĥ¼
    -0.55
    POSITIVE LOGITS
    adin
    0.73
    ainted
    0.71
    creen
    0.71
    hops
    0.70
    hin
    0.69
    aints
    0.69
     surn
    0.67
     mentioned
    0.66
    hips
    0.66
    hots
    0.65
    Act Density 0.193%

    No Known Activations