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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äħż
    -0.14
    NES
    -0.14
    orpor
    -0.14
    bios
    -0.14
     Force
    -0.14
     barg
    -0.13
    porn
    -0.13
    æĬ¼
    -0.13
    lse
    -0.13
    udeau
    -0.13
    POSITIVE LOGITS
    akh
    0.15
    akk
    0.15
    abis
    0.15
    kaar
    0.15
    tings
    0.15
    duit
    0.15
    vel
    0.14
    uria
    0.14
    dao
    0.14
     Ùħرک
    0.14
    Act Density 0.082%

    No Known Activations