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

    Neuronpedia

    INDEX
    Explanations

    quoted strings and their associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.15
    amburger
    -0.15
    fty
    -0.15
    aign
    -0.15
    dess
    -0.15
    igan
    -0.14
    iers
    -0.14
    abet
    -0.14
    acent
    -0.13
    azzo
    -0.13
    POSITIVE LOGITS
    affer
    0.19
    าย
    0.16
    yles
    0.15
     Sist
    0.14
    hue
    0.14
     Coalition
    0.14
     Sof
    0.14
     Kurum
    0.14
    SEX
    0.13
    riage
    0.13
    Act Density 0.083%

    No Known Activations