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

    Neuronpedia

    INDEX
    Explanations

    words related to abilities or capabilities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cot
    -0.88
    cott
    -0.74
    meric
    -0.72
    cation
    -0.70
    mol
    -0.68
    MY
    -0.68
    BA
    -0.67
    hound
    -0.66
    eye
    -0.66
     Physicians
    -0.65
    POSITIVE LOGITS
    bodied
    0.93
    nesses
    0.92
    ufact
    0.88
    ioned
    0.83
    ¶ħ
    0.82
    icient
    0.81
     imag
    0.80
     enough
    0.78
    ansas
    0.77
    itude
    0.75
    Act Density 1.120%

    No Known Activations