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

    Neuronpedia

    INDEX
    Explanations

    the structure of test cases or assertions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acier
    -0.17
    lick
    -0.16
    bih
    -0.16
    apg
    -0.15
    ondon
    -0.15
    ewire
    -0.15
    eness
    -0.15
    ITERAL
    -0.15
    elves
    -0.15
    mong
    -0.14
    POSITIVE LOGITS
     lim
    0.16
    Extras
    0.15
    ison
    0.15
    çIJĨ
    0.14
    acons
    0.14
    999
    0.14
    ɵ
    0.14
     Ivanka
    0.14
     ambient
    0.14
    lim
    0.14
    Act Density 0.017%

    No Known Activations