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

    Neuronpedia

    INDEX
    Explanations

    references to availability and usage of items within a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.19
     Majefty
    -0.98
     Houſe
    -0.96
     myſelf
    -0.96
     Efq
    -0.94
    LookAnd
    -0.93
     purpoſe
    -0.93
     poffible
    -0.93
     houſe
    -0.91
     greateſt
    -0.91
    POSITIVE LOGITS
    .
    0.65
     
    0.51
    :
    0.48
    *
    0.48
    ,\,
    0.47
    Th
    0.47
    .,
    0.47
    잔
    0.47
    </i>
    0.45
    !
    0.44
    Act Density 0.225%

    No Known Activations