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

    Neuronpedia

    INDEX
    Explanations

    terms related to an intermediate state or condition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intermediate and transitional states or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oran
    -0.87
    ille
    -0.81
    ILLE
    -0.78
    ila
    -0.78
    esome
    -0.77
    kie
    -0.76
    lam
    -0.76
    onom
    -0.75
    ÅŁ
    -0.75
    haw
    -0.73
    POSITIVE LOGITS
     intermedi
    0.83
     between
    0.77
     step
    0.76
     grades
    0.75
     intermediate
    0.74
     stages
    0.73
     steps
    0.70
     crossings
    0.70
     separating
    0.69
    between
    0.68
    Act Density 0.022%

    No Known Activations