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

    Neuronpedia

    INDEX
    Explanations

    references to contrasting ideas or comparisons between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.71
    原始内容存档于
    -0.59
    گاری
    -0.57
     versie
    -0.56
    reportWebVitals
    -0.55
    Purity
    -0.53
     Misa
    -0.52
    Spoljašnje
    -0.52
    ChromeDriver
    -0.52
     Poznań
    -0.51
    POSITIVE LOGITS
     front
    0.89
    EndInit
    0.74
     outside
    0.73
    onthe
    0.73
    DIPSETTING
    0.71
    AsUp
    0.70
    Outside
    0.68
     Outside
    0.68
    front
    0.66
     side
    0.66
    Act Density 0.148%

    No Known Activations