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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "away" indicating distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spatial distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laiton
    -0.41
     térm
    -0.36
     Pada
    -0.35
     Democrá
    -0.35
     hidrá
    -0.35
     Púb
    -0.35
     ReSharper
    -0.35
     exécut
    -0.34
    //=
    -0.34
     productivo
    -0.34
    POSITIVE LOGITS
    Nearby
    0.74
     nearby
    0.72
     distant
    0.70
     AWAY
    0.69
     Nearby
    0.69
     Away
    0.66
    nearby
    0.66
     away
    0.64
    distant
    0.64
    Away
    0.63
    Act Density 0.005%

    No Known Activations