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

    Neuronpedia

    INDEX
    Explanations

    phrases that express requests or desires

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

    telling something to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قایناق‌لار
    -0.42
     Pesquisa
    -0.41
    adaptiveStyles
    -0.39
    Jîn
    -0.39
    tagHelperRunner
    -0.39
    يكب
    -0.39
    SourceChecksum
    -0.38
     ErrIntOverflow
    -0.37
    >(&
    -0.36
    馳走
    -0.35
    POSITIVE LOGITS
    MessageOf
    0.46
    ORAGE
    0.45
    brtc
    0.45
    ceğine
    0.43
    ulemon
    0.42
    LETIN
    0.42
    sqcup
    0.42
     Italijanski
    0.42
     deport
    0.41
     betweenstory
    0.40
    Act Density 0.083%

    No Known Activations