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

    Neuronpedia

    INDEX
    Explanations

    mentions of local communities or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to local entities or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.80
    _-
    -0.79
    orst
    -0.79
    uberty
    -0.78
    ERSON
    -0.78
    hower
    -0.77
    --+
    -0.75
    gerald
    -0.72
    rett
    -0.71
    enment
    -0.70
    POSITIVE LOGITS
    ities
    1.19
    ised
    1.12
    izations
    1.11
    isation
    1.03
    ization
    1.03
    ized
    1.00
    izable
    0.91
    izing
    0.90
    izers
    0.90
    izes
    0.89
    Act Density 0.057%

    No Known Activations