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

    Neuronpedia

    INDEX
    Explanations

    references to new brand products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    optera
    -0.17
    peria
    -0.16
    bral
    -0.16
    ÑģÑı
    -0.15
    orda
    -0.15
    .Angle
    -0.15
     setattr
    -0.15
    OTO
    -0.15
    одÑĥ
    -0.15
    nih
    -0.14
    POSITIVE LOGITS
    enburg
    0.35
    ishing
    0.29
    ished
    0.27
     spanking
    0.24
    -new
    0.23
    ishment
    0.21
    -name
    0.21
     span
    0.20
    ishes
    0.19
    -span
    0.18
    Act Density 0.010%

    No Known Activations