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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or transition in time

    oai_token-act-pair · gpt-3.5-turbo

    present tense verbs and phrases indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patel
    -0.70
     Pengu
    -0.69
    amba
    -0.68
     Carib
    -0.62
     similarity
    -0.60
     Balloon
    -0.59
     Pes
    -0.59
     beforehand
    -0.58
     Huss
    -0.57
     spont
    -0.57
    POSITIVE LOGITS
    here
    0.76
    hops
    0.73
    EEK
    0.69
    adays
    0.68
    aukee
    0.68
    YA
    0.67
    enium
    0.66
    WIND
    0.66
    Ô
    0.65
    YP
    0.63
    Act Density 0.382%

    No Known Activations