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

    Neuronpedia

    INDEX
    Explanations

    references to specific subjects or entities within a legal or formal context

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

    Follows "to which" or similar relational phrases

    np_acts-logits-general · gemini-2.0-flash

    to which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.70
     ""],
    -0.61
    orianCalendar
    -0.60
    enfance
    -0.60
    (!__
    -0.59
     récomp
    -0.58
    =$?
    -0.56
    -0.56
    KommentareTeilen
    -0.56
    NameInMap
    -0.56
    POSITIVE LOGITS
     nawr
    0.54
     link
    0.54
     relate
    0.49
     related
    0.49
     relates
    0.49
     belong
    0.48
     RUSH
    0.48
     rush
    0.48
     belonging
    0.46
    link
    0.46
    Act Density 0.065%

    No Known Activations