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

    Neuronpedia

    INDEX
    Explanations

    references to judgments and legal or moral authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dochter
    -0.44
     PERMAN
    -0.39
    ፩
    -0.35
     Permanent
    -0.35
     passer
    -0.35
     Perman
    -0.35
    されます
    -0.34
    Huile
    -0.34
     perman
    -0.33
     insufic
    -0.33
    POSITIVE LOGITS
     EconPapers
    0.82
    abestanden
    0.57
    KommentareTeilen
    0.56
     iconLine
    0.53
     OMITBAD
    0.52
     ويكيپيديا
    0.51
    ніципа
    0.50
     Majefty
    0.46
    Beskrivelse
    0.46
    点此举报
    0.46
    Act Density 0.309%

    No Known Activations