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

    Neuronpedia

    INDEX
    Explanations

    references to problematic or negative situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancode
    -0.15
    $MESS
    -0.15
    æIJŀ
    -0.15
    plusplus
    -0.15
    LOUR
    -0.15
    ville
    -0.15
    VILLE
    -0.14
    léd
    -0.14
     Pey
    -0.14
    aklı
    -0.14
    POSITIVE LOGITS
     schem
    0.14
    èĻ«
    0.14
    arg
    0.14
    åĬ
    0.14
    alm
    0.14
     zoom
    0.14
     bach
    0.14
    ee
    0.14
     even
    0.14
    imen
    0.14
    Act Density 0.008%

    No Known Activations