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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and continuity of actions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.86
    IUrlHelper
    -0.81
    setVerticalGroup
    -0.80
    ":[{
    -0.78
    ########.
    -0.78
    __":
    -0.76
     HasFactory
    -0.72
    lapsingToolbar
    -0.72
    TypedDataSet
    -0.72
     jScrollPane
    -0.71
    POSITIVE LOGITS
     Always
    1.16
    Always
    1.14
    always
    1.08
     always
    1.07
     ALWAYS
    1.04
    ALWAYS
    0.97
     Toujours
    0.97
    deauna
    0.96
    Never
    0.95
     never
    0.95
    Act Density 0.226%

    No Known Activations