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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting cues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ije
    -0.20
    reff
    -0.15
     secretive
    -0.15
    ë¡ľëĵľ
    -0.15
    apos
    -0.14
    vier
    -0.14
     Lime
    -0.14
    antino
    -0.14
     Brass
    -0.13
    insk
    -0.13
    POSITIVE LOGITS
    omor
    0.18
    (SP
    0.17
    (Image
    0.16
    earn
    0.16
    -fw
    0.15
    ubern
    0.14
    480
    0.14
    umbn
    0.14
    UTERS
    0.14
     ÑĤÑĢÑĥ
    0.14
    Act Density 0.081%

    No Known Activations