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

    Neuronpedia

    INDEX
    Explanations

    phrases related to editing and textual changes in literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.44
     ''
    -1.37
    ”—
    -1.30
    .”—
    -1.29
    —-
    -1.28
    〜
    -1.19
    \-
    -1.15
    —
    -1.15
    
    -1.14
    \_
    -1.12
    POSITIVE LOGITS
     –
    2.58
     –,
    1.40
     أيضاً
    1.24
    ്‍
    1.15
    اً
    1.10
    راً
    1.08
    ায়
    1.07
    ര്‍
    1.05
    ല്‍
    1.04
    باً
    1.03
    Act Density 0.439%

    No Known Activations