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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or guidance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    staking
    -0.67
     alot
    -0.64
    ewitness
    -0.61
    estern
    -0.59
     mathemat
    -0.58
    âĸ¬âĸ¬
    -0.56
    ailable
    -0.54
     tremend
    -0.54
     compr
    -0.52
    arlane
    -0.51
    POSITIVE LOGITS
     afterward
    1.35
     thereafter
    1.09
     afterwards
    1.07
    .).
    0.92
     later
    0.91
    .)
    0.89
     anyway
    0.86
     someday
    0.86
     beforehand
    0.85
    .]
    0.85
    Act Density 0.701%

    No Known Activations