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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and expressions related to opposition or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anel
    -0.16
    ibold
    -0.16
    ican
    -0.15
    tep
    -0.15
    ndon
    -0.15
     MÃ¼ÅŁ
    -0.14
    lili
    -0.14
    áy
    -0.14
    æk
    -0.14
    onis
    -0.14
    POSITIVE LOGITS
     necessarily
    0.23
     sugar
    0.17
     rein
    0.17
     judgment
    0.17
     ever
    0.17
     judgement
    0.16
     conforms
    0.15
     conform
    0.15
     Limits
    0.15
     limit
    0.15
    Act Density 0.196%

    No Known Activations