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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing satire or irony

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,
    -0.52
     even
    -0.49
     I
    -0.46
    AddColumn
    -0.46
    .
    -0.46
    …
    -0.44
     sometimes
    -0.44
     it
    -0.44
     It
    -0.42
     especially
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.93
     متعلقه
    0.91
     للمعارف
    0.88
    0.88
     raiſ
    0.86
    StoryboardSegue
    0.84
    OGND
    0.79
    WebVitals
    0.79
     myſelf
    0.79
     wireType
    0.78
    Act Density 0.300%

    No Known Activations