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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licit
    -0.16
    ould
    -0.15
    [
    -0.14
    ushman
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    ULT
    -0.14
     èĹ
    -0.14
    nde
    -0.13
    .EntityFramework
    -0.13
     Horny
    -0.13
    POSITIVE LOGITS
     karak
    0.18
     Cheat
    0.15
    sert
    0.15
    ermal
    0.15
    eno
    0.15
     accountability
    0.14
    gni
    0.14
    kus
    0.14
    áºŃt
    0.14
    adb
    0.14
    Act Density 0.185%

    No Known Activations