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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning the applicability or relevance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rând
    -0.81
    ]--;
    -0.79
     pleaſure
    -0.77
     ſame
    -0.74
    lccccc
    -0.73
     houſe
    -0.73
    BibitemShut
    -0.73
    ^(@)
    -0.72
     Finlay
    -0.72
     uſed
    -0.71
    POSITIVE LOGITS
    SuppressMessage
    0.69
    TypedDataSet
    0.68
     why
    0.67
     HasFactory
    0.60
    MarshalTo
    0.59
    rungsseite
    0.59
    apimachinery
    0.58
    AssignableFrom
    0.58
     LoggerFactory
    0.58
     GenerationType
    0.58
    Act Density 0.009%

    No Known Activations