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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iri
    -0.16
    eyer
    -0.14
    292
    -0.14
     Bauer
    -0.14
    vent
    -0.14
    ocht
    -0.14
    κÏħ
    -0.14
    lx
    -0.14
    rophe
    -0.13
    ä»Ĭå¹´
    -0.13
    POSITIVE LOGITS
     rumor
    0.17
     Atlas
    0.15
     cr
    0.15
    Atlas
    0.14
    amat
    0.14
    aber
    0.14
     Cr
    0.14
    oy
    0.14
    assa
    0.14
    éİ®
    0.14
    Act Density 0.005%

    No Known Activations