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

    Neuronpedia

    INDEX
    Explanations

    things or concepts that are well-known or recognized

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    chance
    -1.33
    reen
    -1.16
    \\\\\\\\\\\\\\\\
    -1.13
    prus
    -1.10
    tan
    -1.09
    psey
    -1.09
    secution
    -1.07
    ree
    -1.04
    ©¶æ
    -1.03
    tein
    -1.02
    POSITIVE LOGITS
    ity
    1.33
    ized
    1.29
    ities
    1.27
    ization
    1.26
    izing
    1.25
    sworth
    1.21
    icity
    1.19
    izations
    1.18
    idad
    1.14
     enough
    1.14
    Act Density 0.892%

    No Known Activations