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

    Neuronpedia

    INDEX
    Explanations

    statements or descriptions emphasizing power or strength

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "powerful."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.76
    chal
    -0.76
    thus
    -0.72
     Fever
    -0.71
    roma
    -0.70
     Destination
    -0.70
    arthed
    -0.68
    den
    -0.68
    ©¶æ
    -0.66
     Myster
    -0.65
    POSITIVE LOGITS
     powerful
    1.07
     chords
    0.95
    powerful
    0.89
     enough
    0.88
    iazep
    0.82
     oppress
    0.81
     hitters
    0.81
     levers
    0.78
     glim
    0.78
     intimid
    0.78
    Act Density 0.013%

    No Known Activations