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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inquiries or requests for assistance and information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    disp
    -0.16
    presso
    -0.15
    uin
    -0.14
    ONO
    -0.14
     dat
    -0.14
     thất
    -0.14
    yen
    -0.14
     invalid
    -0.14
     Martial
    -0.14
    è³¢
    -0.13
    POSITIVE LOGITS
    pty
    0.15
    abwe
    0.15
     Shield
    0.14
    vide
    0.14
    Inline
    0.14
     {?>↵
    0.13
     shielding
    0.13
    óz
    0.13
     wager
    0.13
    åѦéĻ¢
    0.13
    Act Density 0.049%

    No Known Activations