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

    Neuronpedia

    INDEX
    Explanations

    assertions used in testing code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyh
    -0.13
     Bans
    -0.13
    .ns
    -0.13
    'gc
    -0.13
    ulaire
    -0.13
    hee
    -0.13
    grese
    -0.13
    esz
    -0.13
    決å®ļ
    -0.12
    heimer
    -0.12
    POSITIVE LOGITS
     True
    0.33
    True
    0.33
    _EQ
    0.31
     true
    0.30
     TRUE
    0.29
    Equal
    0.28
    _eq
    0.28
    _true
    0.28
    _TRUE
    0.28
    TRUE
    0.28
    Act Density 0.008%

    No Known Activations