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

    Neuronpedia

    INDEX
    Explanations

    equations and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sex
    -0.15
    ecure
    -0.15
    riba
    -0.15
    inha
    -0.15
    æĭ³
    -0.14
     Sex
    -0.14
     transfer
    -0.14
    alah
    -0.14
    peria
    -0.14
    acock
    -0.14
    POSITIVE LOGITS
    .dot
    0.20
     Dot
    0.18
    .Dot
    0.18
     dot
    0.17
    /me
    0.17
    razier
    0.16
    (dot
    0.15
     Norm
    0.15
     TRACE
    0.14
    994
    0.14
    Act Density 0.129%

    No Known Activations