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

    Neuronpedia

    INDEX
    Explanations

    capable of phrases, indicating abilities or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    the word "capable" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.71
    cot
    -0.67
    cott
    -0.67
    mol
    -0.65
     Moz
    -0.63
    meric
    -0.62
    BA
    -0.61
    MY
    -0.61
     Von
    -0.60
     Schwarz
    -0.60
    POSITIVE LOGITS
    nesses
    0.92
    bodied
    0.90
    icient
    0.78
     imag
    0.75
    ufact
    0.72
     impairment
    0.72
    itude
    0.71
     enough
    0.70
     accompl
    0.69
    ioned
    0.68
    Act Density 0.021%

    No Known Activations