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

    Neuronpedia

    INDEX
    Explanations

    negative numeric values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.68
    ($__
    -0.67
    diali
    -0.61
     tartalomajánló
    -0.60
    帖最后由
    -0.60
    }")]
    -0.59
    Дереккөздер
    -0.57
     EconPapers
    -0.57
    Sucesor
    -0.57
     Autorisations
    -0.56
    POSITIVE LOGITS
    Meno
    0.51
    CJK
    0.51
    tvguidetime
    0.51
     BorderSide
    0.49
    enumi
    0.48
     testa
    0.47
     volto
    0.46
    MLLoader
    0.46
    Eyed
    0.46
    MIDDLEWARE
    0.45
    Act Density 0.098%

    No Known Activations