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

    Neuronpedia

    INDEX
    Explanations

    phrases related to "peak" performance, intensity, experience, or output

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    icate
    -0.84
    oured
    -0.78
    onsense
    -0.76
    ktop
    -0.74
    erie
    -0.73
    signed
    -0.73
     transpl
    -0.72
    estern
    -0.70
    recated
    -0.69
    optional
    -0.67
    POSITIVE LOGITS
     erection
    0.78
    imum
    0.74
     peaks
    0.72
    lite
    0.71
     occupancy
    0.70
    urb
    0.69
     heights
    0.69
     height
    0.68
     brightness
    0.68
    ceed
    0.67
    Act Density 8.447%

    No Known Activations