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

    Neuronpedia

    INDEX
    Explanations

    phrases and clauses that are likely to indicate a continuation or elaboration in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.70
     Sabha
    -0.64
     Tid
    -0.64
     RAD
    -0.60
     Chou
    -0.60
     Sandy
    -0.59
     airs
    -0.59
     wide
    -0.59
     Osw
    -0.59
     Manhattan
    -0.58
    POSITIVE LOGITS
    ¤
    1.21
    ª
    1.14
    Ń
    1.11
    ¡
    1.11
    «
    1.08
    ľ
    1.07
    £
    1.07
    Ļ
    1.06
    ĺ
    1.05
    ¼
    1.03
    Act Density 0.343%

    No Known Activations