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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses and words related to the concept of wings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cejas
    -0.54
     ruinas
    -0.47
     desmotivaciones
    -0.46
     escote
    -0.45
     futbolista
    -0.43
     exportaciones
    -0.42
     rodillas
    -0.42
     agujas
    -0.42
    monials
    -0.41
    niająca
    -0.41
    POSITIVE LOGITS
    saraba
    0.60
     wing
    0.60
    EDEFAULT
    0.59
    science
    0.58
     buck
    0.57
     Buck
    0.57
     science
    0.54
    Buck
    0.52
    +#+
    0.52
    buck
    0.51
    Act Density 0.215%

    No Known Activations