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

    Neuronpedia

    INDEX
    Explanations

    references to new products or additions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    одÑĥ
    -0.19
    optera
    -0.17
    orda
    -0.15
    bral
    -0.15
    peria
    -0.15
    uhan
    -0.15
    ÑģÑı
    -0.14
    .uf
    -0.14
    bower
    -0.14
    .Angle
    -0.14
    POSITIVE LOGITS
    enburg
    0.32
    ishing
    0.28
    ished
    0.25
     spanking
    0.22
    -new
    0.21
    -name
    0.19
    ishment
    0.19
    idd
    0.17
    -n
    0.17
    ishes
    0.17
    Act Density 0.006%

    No Known Activations