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

    Neuronpedia

    INDEX
    Explanations

    lists or catalogs

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.77
    roth
    -0.75
    factor
    -0.67
    sters
    -0.66
    wash
    -0.64
    venge
    -0.64
    WT
    -0.64
    tek
    -0.63
    model
    -0.63
    medium
    -0.63
    POSITIVE LOGITS
     acron
    0.81
     endorsements
    0.81
     contents
    0.80
     names
    0.79
     accomplishments
    0.78
     entries
    0.77
     items
    0.77
     thoughts
    0.74
     links
    0.73
     listings
    0.73
    Act Density 0.264%

    No Known Activations