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

    Neuronpedia

    INDEX
    Explanations

    descriptive language related to events and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avana
    -0.16
    ouri
    -0.15
    ç¯
    -0.14
     Ø°
    -0.14
    [of
    -0.14
    248
    -0.13
    ousand
    -0.13
    пон
    -0.13
    oll
    -0.13
    cid
    -0.13
    POSITIVE LOGITS
     behind
    0.27
    Behind
    0.21
     Behind
    0.20
     underneath
    0.20
    beh
    0.18
     beneath
    0.18
     Bene
    0.17
     ÑģпÑĢава
    0.17
     xung
    0.17
    ARIO
    0.16
    Act Density 0.294%

    No Known Activations