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

    Neuronpedia

    INDEX
    Explanations

    references to people's names or nicknames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĨIJ
    -0.16
    åĤ
    -0.15
    dz
    -0.14
    USR
    -0.14
    ulously
    -0.14
    ways
    -0.14
    818
    -0.14
    edium
    -0.14
    ths
    -0.13
    nech
    -0.13
    POSITIVE LOGITS
    acock
    0.28
    oria
    0.23
    aches
    0.22
    ugeot
    0.22
    formance
    0.21
    eling
    0.21
    anuts
    0.21
    ACE
    0.21
    oples
    0.20
    uliar
    0.19
    Act Density 0.011%

    No Known Activations