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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and personal connections

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

    Follows punctuation or certain symbols

    np_acts-logits-general · gemini-2.0-flash

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrBuilder
    -0.71
    tanleria
    -0.64
    OGND
    -0.59
     –,
    -0.59
    AccessorTable
    -0.59
     ―――――
    -0.58
    SequentialGroup
    -0.53
     iconFacebook
    -0.53
     ویکی‌پدی
    -0.53
    %)$
    -0.52
    POSITIVE LOGITS
     they
    0.67
     it
    0.66
     ,
    0.56
     there
    0.51
     its
    0.50
     sorry
    0.49
     nothing
    0.48
     ayrıca
    0.48
     we
    0.48
    they
    0.47
    Act Density 0.587%

    No Known Activations