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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "both" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sey
    -0.16
    edo
    -0.15
    iert
    -0.15
    urg
    -0.15
    atin
    -0.14
     Salisbury
    -0.14
    hiro
    -0.14
    iments
    -0.14
    /use
    -0.13
    abol
    -0.13
    POSITIVE LOGITS
    resi
    0.16
    irs
    0.16
    rav
    0.15
    ést
    0.15
    ì½ĺ
    0.14
    ENDOR
    0.14
    ë§ī
    0.14
    Arena
    0.14
    FTA
    0.14
    ravel
    0.14
    Act Density 0.025%

    No Known Activations