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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coding languages

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or ellipses indicating pauses or omissions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.81
    ously
    -0.80
     Galile
    -0.77
     Krug
    -0.69
     suspic
    -0.68
    xes
    -0.67
    uers
    -0.67
     slope
    -0.66
     slopes
    -0.63
    opol
    -0.63
    POSITIVE LOGITS
    etc
    1.03
    walking
    0.91
    MORE
    0.84
    please
    0.82
    taboola
    0.81
    SER
    0.78
     fixme
    0.76
    WOR
    0.75
    sym
    0.75
    orders
    0.75
    Act Density 0.013%

    No Known Activations