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

    Neuronpedia

    INDEX
    Explanations

    negative adjectives or descriptors related to problematic or undesirable situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dex
    -0.18
     Dillon
    -0.16
    igung
    -0.14
    æĸ¹
    -0.14
    HITE
    -0.14
    ém
    -0.14
    swire
    -0.14
    ç¦
    -0.13
    ots
    -0.13
    'gc
    -0.13
    POSITIVE LOGITS
    onor
    0.16
    iti
    0.15
     Cry
    0.14
    icol
    0.14
    äch
    0.14
    æĹĹ
    0.14
    ellig
    0.14
    ĮĢ
    0.13
    ypo
    0.13
    uli
    0.13
    Act Density 0.014%

    No Known Activations