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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to personal names and places

    oai_token-act-pair · gpt-3.5-turbo

    words related to the notion of nature and environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.76
    ittal
    -0.72
    unity
    -0.67
    inances
    -0.67
    inately
    -0.66
    ublic
    -0.65
    inated
    -0.64
    inate
    -0.63
    heses
    -0.63
    inating
    -0.62
    POSITIVE LOGITS
    tes
    0.77
    lis
    0.76
    bye
    0.71
    jriwal
    0.70
    tarian
    0.69
    leaf
    0.68
    eers
    0.67
    rencies
    0.66
    olesc
    0.65
    atoes
    0.65
    Act Density 0.069%

    No Known Activations