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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and expressions of limitation or constraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©
    -0.16
    $MESS
    -0.15
    izr
    -0.14
    еви
    -0.14
     DESC
    -0.14
    Ľ°
    -0.14
    adro
    -0.14
     Slug
    -0.14
    ewis
    -0.14
    ellig
    -0.14
    POSITIVE LOGITS
     Roths
    0.16
    à¤Ĥà¤Ł
    0.15
    оÑĢдин
    0.14
    arin
    0.14
    æµģ
    0.14
    TEL
    0.14
    avers
    0.14
    SCO
    0.14
    åŃĿ
    0.14
    haven
    0.14
    Act Density 0.003%

    No Known Activations