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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and separators in a textual context

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

    punctuation and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dead
    -0.37
     tra
    -0.34
     sur
    -0.34
     mad
    -0.33
     contra
    -0.32
     Rol
    -0.32
     Scar
    -0.31
     MAD
    -0.31
     Mada
    -0.30
     Tam
    -0.30
    POSITIVE LOGITS
    UnusedPrivate
    0.78
     للمعارف
    0.77
    Diweddarwch
    0.75
    AndEndTag
    0.73
    RegressionTest
    0.72
    Personensuche
    0.66
    <unused52>
    0.64
    <unused41>
    0.63
    <unused28>
    0.63
    <unused3>
    0.63
    Act Density 0.224%

    No Known Activations