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

    Neuronpedia

    INDEX
    Explanations

    phrases that signal the beginning of a list or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zd
    -0.15
    remen
    -0.15
    /place
    -0.15
     Erk
    -0.14
    cken
    -0.14
    lite
    -0.14
    ÑıÑĤи
    -0.14
     Trib
    -0.14
     Demir
    -0.14
    à¥įà¤
    -0.14
    POSITIVE LOGITS
    -average
    0.21
    neath
    0.18
    /up
    0.18
    -zero
    0.17
    /out
    0.15
     freezing
    0.15
     decks
    0.15
    oup
    0.15
    .gdx
    0.15
    stairs
    0.15
    Act Density 0.020%

    No Known Activations