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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong emotions or feelings of satisfaction

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

    conjunctions and discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.69
    ArgsConstructor
    -0.68
    Билгалдахарш
    -0.63
     utafitiHapana
    -0.60
    WebVitals
    -0.60
     EconPapers
    -0.59
    FromNib
    -0.58
    rungsseite
    -0.57
     ujednoznacz
    -0.56
    Дереккөздер
    -0.56
    POSITIVE LOGITS
    The
    0.49
    AndEndTag
    0.47
    While
    0.44
    Though
    0.43
    Using
    0.41
    Perhaps
    0.40
    Following
    0.40
     Though
    0.39
    stützung
    0.36
    “
    0.36
    Act Density 0.009%

    No Known Activations