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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to strength or power

    oai_token-act-pair · gpt-3.5-turbo

    the word "powerful" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chal
    -0.84
    forth
    -0.81
     Myster
    -0.79
     Fever
    -0.78
    den
    -0.73
    cision
    -0.72
    thus
    -0.71
    arthed
    -0.70
    aternity
    -0.69
    ilk
    -0.69
    POSITIVE LOGITS
     chords
    1.06
     enough
    0.89
     chord
    0.88
     hitters
    0.83
     impulses
    0.82
     levers
    0.81
     powerful
    0.81
     blows
    0.80
     fry
    0.78
     motiv
    0.77
    Act Density 0.016%

    No Known Activations