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

    Neuronpedia

    INDEX
    Explanations

    mentions of various events or occurrences involving specific details

    oai_token-act-pair · gpt-3.5-turbo

    references that introduce examples or specifics within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bell
    -0.79
    ilion
    -0.72
    aya
    -0.69
    iny
    -0.69
    ike
    -0.69
    idate
    -0.68
    client
    -0.67
    roud
    -0.67
    iet
    -0.67
    SPONSORED
    -0.67
    POSITIVE LOGITS
     ones
    1.21
     those
    1.14
     ours
    0.95
     yours
    0.90
     some
    0.89
     one
    0.83
     several
    0.78
    those
    0.75
     hers
    0.74
    lihood
    0.73
    Act Density 0.063%

    No Known Activations