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

    Neuronpedia

    INDEX
    Explanations

    queries seeking clarification or definitions of terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     only
    -0.91
     nowhere
    -0.87
    only
    -0.82
    Only
    -0.77
     Only
    -0.73
    never
    -0.71
     apenas
    -0.70
     never
    -0.70
    nothing
    -0.70
     seldom
    -0.68
    POSITIVE LOGITS
     exactly
    1.49
    exactly
    1.29
     exactamente
    1.25
     exactement
    1.24
     Exactly
    1.17
     precies
    1.11
     actually
    1.09
     esattamente
    1.06
     EXACTLY
    1.04
     ACTUALLY
    1.04
    Act Density 0.559%

    No Known Activations