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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated uncertainties or ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.38
    findpost
    -0.38
     pleaſure
    -0.35
     uſed
    -0.35
     paſſ
    -0.35
     مشين
    -0.34
     ſche
    -0.33
    =’
    -0.33
     HasFactory
    -0.31
     itſelf
    -0.31
    POSITIVE LOGITS
     ±
    1.13
    ±
    1.06
     (±
    0.94
     +/-
    0.88
     ± 
    0.88
    pm
    0.81
    0.77
    +/-
    0.76
    ⫾
    0.68
     <=",
    0.63
    Act Density 0.406%

    No Known Activations