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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly exclamation points and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.16
    ény
    -0.16
    PLE
    -0.14
    wiki
    -0.14
    ŀĭ
    -0.14
    ield
    -0.14
    iard
    -0.14
     tra
    -0.14
    plx
    -0.13
    zej
    -0.13
    POSITIVE LOGITS
    _DEPRECATED
    0.15
    abor
    0.15
    dez
    0.15
    .cx
    0.15
    ise
    0.15
    illac
    0.14
     nues
    0.14
    izzie
    0.14
    eras
    0.14
    ombat
    0.14
    Act Density 0.006%

    No Known Activations