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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or considerations in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sink
    -0.33
    lorette
    -0.30
    sourceforge
    -0.30
     triggered
    -0.29
     visitor
    -0.29
     silently
    -0.28
    mayor
    -0.28
     accompanied
    -0.28
     user
    -0.28
    setCode
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.79
     dotyczące
    0.74
    Concerning
    0.74
    Regarding
    0.73
     bezüglich
    0.72
    tableFuture
    0.72
     Concerning
    0.71
     betreft
    0.68
     regarding
    0.68
     riguardo
    0.68
    Act Density 0.235%

    No Known Activations