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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and phrases related to interpersonal relationships or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dual
    -0.18
    -0.17
    Dual
    -0.15
    504
    -0.15
     Berger
    -0.15
     dual
    -0.15
     still
    -0.14
    ugi
    -0.14
    icus
    -0.14
    xima
    -0.14
    POSITIVE LOGITS
    Ñģок
    0.18
    ÑģÑĤÑĥп
    0.17
    ģ
    0.16
    InSeconds
    0.15
    ARED
    0.15
    ukan
    0.15
    á»iji
    0.15
    _pb
    0.15
    úp
    0.14
    807
    0.13
    Act Density 0.001%

    No Known Activations