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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions that contain special characters or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uſed
    -0.83
     deſt
    -0.80
     raiſ
    -0.77
     Majefty
    -0.77
     purpoſe
    -0.75
     ſaid
    -0.73
     pleaſure
    -0.72
     ſen
    -0.71
     uſ
    -0.70
     ſtate
    -0.69
    POSITIVE LOGITS
    EndContext
    1.15
    AnchorStyles
    0.93
    󠁿
    0.82
    tableFuture
    0.72
    ScopeManager
    0.69
    [toxicity=0]
    0.68
    StandardCharsets
    0.66
    __(/*!
    0.66
    MemoryWarning
    0.65
    mbggenerated
    0.65
    Act Density 0.029%

    No Known Activations