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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific verbs and phrases indicating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning-of-sequence marker that denotes the start of a new document or text segment.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    unknownFields
    -0.66
     متعلقه
    -0.61
    ViewInit
    -0.59
     Bourgoin
    -0.54
     (--
    -0.54
    Personensuche
    -0.54
    RetentionPolicy
    -0.53
    jsonwebtoken
    -0.53
     мәкал
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.71
    AccessorTable
    0.69
     חיצוניים
    0.67
     שוליים
    0.67
     referenties
    0.65
     esterni
    0.62
    ")]
    0.58
    ））
    0.58
    ")){
    0.57
    }}}{\
    0.56
    Act Density 0.324%

    No Known Activations