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

    Neuronpedia

    INDEX
    Explanations

    quotations and punctuation that suggest dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oot
    -0.21
    erman
    -0.19
     nghá»ģ
    -0.17
    ÃĹ↵↵
    -0.16
    alnız
    -0.16
    ial
    -0.16
    ESSAGES
    -0.15
    MBOL
    -0.15
    raquo
    -0.15
    -être
    -0.15
    POSITIVE LOGITS
    cy
    0.19
    angers
    0.15
    elve
    0.15
    ãĥ£
    0.15
    rect
    0.15
     Zuk
    0.15
    Ľå»º
    0.14
    ifiant
    0.14
    ident
    0.14
    lef
    0.14
    Act Density 0.063%

    No Known Activations