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

    Neuronpedia

    INDEX
    Explanations

    references to items, examples, or entities within parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.54
    <bos>
    -0.45
    Hints
    -0.42
    lijker
    -0.42
     it
    -0.42
    ्य
    -0.40
     the
    -0.40
    bitan
    -0.40
    beitung
    -0.40
     شهرد
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.95
     houſe
    0.84
    تقاوى
    0.83
     Houſe
    0.82
    ſelves
    0.79
    GEBURTSDATUM
    0.78
     ſtate
    0.78
     faſt
    0.75
     Reſ
    0.75
    ſelf
    0.75
    Act Density 0.446%

    No Known Activations