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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.94
     Theſe
    -0.86
     themſelves
    -0.85
     myſelf
    -0.85
    ".
    -0.84
     Houſe
    -0.81
     Efq
    -0.80
     ་་
    -0.79
    .";
    -0.78
     Jefus
    -0.76
    POSITIVE LOGITS
     said
    0.49
    .,
    0.47
     voix
    0.46
    <eos>
    0.46
    hoodie
    0.45
    ISupport
    0.44
     commented
    0.42
    、
    0.42
     sagde
    0.41
    ,
    0.41
    Act Density 0.180%

    No Known Activations