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

    Neuronpedia

    INDEX
    Explanations

    references to "Local" entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to local systems or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.81
    olicy
    -0.80
    xual
    -0.75
    gerald
    -0.73
     âĶľ
    -0.72
    ERSON
    -0.72
    swer
    -0.72
    uberty
    -0.71
    _-
    -0.71
    --+
    -0.70
    POSITIVE LOGITS
    ised
    1.32
    isation
    1.28
    izations
    1.26
    ization
    1.25
    ities
    1.25
    ized
    1.16
    izing
    1.11
    izable
    1.06
    isations
    1.03
    izes
    1.03
    Act Density 0.042%

    No Known Activations