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

    Neuronpedia

    INDEX
    Explanations

    conversational and relational expressions commonly used in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.80
    ValueStyle
    -0.75
     للاسماء
    -0.63
     bezeichneter
    -0.60
     “
    -0.60
    rungsseite
    -0.59
    )))))
    -0.54
    intele
    -0.54
    ↵↵
    -0.54
     дописавши
    -0.54
    POSITIVE LOGITS
     MainAxisSize
    0.79
    tvguidetime
    0.73
     estekak
    0.72
    ...".
    0.69
    IntoConstraints
    0.68
    </b>
    0.68
    </strong>
    0.68
    UserScript
    0.68
    ImageContext
    0.65
    </u>
    0.64
    Act Density 0.181%

    No Known Activations