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

    Neuronpedia

    INDEX
    Explanations

    questions about knowledge or understanding

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ishable
    -1.14
    otom
    -1.13
    isco
    -1.07
    izont
    -1.06
    attery
    -1.05
    stros
    -1.03
    ouls
    -1.03
    acco
    -1.02
    aez
    -1.02
    interstitial
    -1.01
    POSITIVE LOGITS
     how
    1.29
    lege
    1.18
     exactly
    1.15
     whether
    1.06
     why
    1.05
     what
    1.01
     ABOUT
    1.01
    ledge
    1.00
    ledged
    0.97
     about
    0.96
    Act Density 0.336%

    No Known Activations