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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "before" and its variations, indicating a focus on temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initComponents
    -0.70
    BrowserModule
    -0.65
    ArrowToggle
    -0.65
     følge
    -0.65
    bolista
    -0.64
    ษัท
    -0.63
    niosek
    -0.61
    SerializedSize
    -0.58
    Puss
    -0.58
    %)$
    -0.58
    POSITIVE LOGITS
    hand
    0.98
     anything
    0.82
     proceeding
    0.81
     embarking
    0.79
     any
    0.78
    andafter
    0.77
     anyone
    0.76
    HAND
    0.75
     dawn
    0.70
     they
    0.68
    Act Density 0.104%

    No Known Activations