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

    Neuronpedia

    INDEX
    Explanations

    the presence of opening tokens in structured text formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.84
     незавершена
    -0.76
    StructEnd
    -0.75
    Portály
    -0.71
    CloseOperation
    -0.70
     فريبيس
    -0.70
    izophrenia
    -0.69
     ddelweddau
    -0.68
    SharedDtor
    -0.67
    StoryboardSegue
    -0.64
    POSITIVE LOGITS
    <em>
    0.97
    <u>
    0.81
    <strong>
    0.76
    <h6>
    0.72
    <code>
    0.72
    <i>
    0.70
     lourdes
    0.69
    </em>
    0.68
    reiter
    0.65
    “
    0.64
    Act Density 0.008%

    No Known Activations