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

    Neuronpedia

    INDEX
    Explanations

    phrases related to claims and obligations

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

    possessive nouns followed by "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '])){
    -0.52
    imanapun
    -0.50
     grave
    -0.46
    切
    -0.46
    ancing
    -0.46
    端
    -0.46
    ьев
    -0.45
    isiert
    -0.45
    Luc
    -0.45
    ike
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.76
     BoxDecoration
    0.71
    تقاوى
    0.67
    tagext
    0.65
     <<<<<<<<<<<<<<
    0.65
     CreateTagHelper
    0.65
     متعلقه
    0.65
     someone
    0.65
     EconPapers
    0.64
    __(/*!
    0.63
    Act Density 0.420%

    No Known Activations