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

    Neuronpedia

    INDEX
    Explanations

    expressions of confirmation or statements made during interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mas
    -0.17
    itoris
    -0.16
    imizer
    -0.15
    ween
    -0.15
    enaire
    -0.15
    links
    -0.14
    ippi
    -0.14
    etur
    -0.14
    plorer
    -0.14
    ÏģαÏĤ
    -0.14
    POSITIVE LOGITS
    outers
    0.15
     Guerr
    0.14
    CTS
    0.14
    ÑĢеж
    0.14
    hazi
    0.13
     Scheme
    0.13
    693
    0.13
     mediation
    0.13
    auses
    0.13
    opr
    0.13
    Act Density 0.069%

    No Known Activations