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

    Neuronpedia

    INDEX
    Explanations

    names, particularly with accents and special characters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or notable figures associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zona
    -0.70
    obyl
    -0.69
    Timeout
    -0.67
    ettings
    -0.66
    hov
    -0.62
     paraly
    -0.61
    Bottom
    -0.61
    indu
    -0.60
     gradient
    -0.60
     pockets
    -0.60
    POSITIVE LOGITS
    ruary
    1.01
    ancial
    0.94
    owship
    0.83
    encer
    0.70
    ortunately
    0.70
     ãĤµ
    0.64
    enhagen
    0.64
    cus
    0.61
    hig
    0.60
     Fighters
    0.60
    Act Density 0.385%

    No Known Activations