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

    Neuronpedia

    INDEX
    Explanations

    terms related to elements of danger and urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentLoaded
    -0.50
     surla
    -0.47
    Drip
    -0.46
     drips
    -0.46
    nodoc
    -0.45
    TypedDataSet
    -0.44
     Walks
    -0.44
     preghi
    -0.44
     Rises
    -0.44
     assiste
    -0.43
    POSITIVE LOGITS
     running
    0.96
     racing
    0.86
     flying
    0.85
     moving
    0.84
     marching
    0.83
     sailing
    0.81
     spr
    0.78
     climbing
    0.76
     traveling
    0.76
     travelling
    0.74
    Act Density 0.516%

    No Known Activations