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

    Neuronpedia

    INDEX
    Explanations

    references to external sources and citations within a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     houſe
    -1.02
     مشين
    -0.98
     myſelf
    -0.97
    ſelves
    -0.97
     ostavi
    -0.96
     Audiodateien
    -0.94
    ſelf
    -0.94
     uſed
    -0.93
     themſelves
    -0.93
    POSITIVE LOGITS
    ↵↵
    0.64
    .
    0.59
     I
    0.57
     A
    0.53
    ?
    0.48
     W
    0.47
     a
    0.47
     
    0.46
     J
    0.46
    \
    0.46
    Act Density 0.031%

    No Known Activations