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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ub
    -0.16
    ALCHEMY
    -0.15
    STRU
    -0.15
    ÙĨاÙĨ
    -0.15
    ento
    -0.15
    ÏģÏĮ
    -0.14
    terra
    -0.14
    DAT
    -0.14
    oric
    -0.13
    éģĬ
    -0.13
    POSITIVE LOGITS
    377
    0.17
    kers
    0.16
    æĨ
    0.16
    376
    0.14
    711
    0.14
    MBProgressHUD
    0.14
    gie
    0.13
    fragment
    0.13
    ERGY
    0.13
    764
    0.13
    Act Density 0.013%

    No Known Activations