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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    αÏĥ
    -0.17
    atak
    -0.16
    ifax
    -0.15
     Tik
    -0.15
    spir
    -0.15
    unik
    -0.14
    serter
    -0.14
    iran
    -0.14
    onom
    -0.14
    helm
    -0.14
    POSITIVE LOGITS
    rys
    0.17
    OPS
    0.15
     tow
    0.15
     Fernandez
    0.14
     crowned
    0.14
     pit
    0.14
    598
    0.14
     HoÃłng
    0.14
    apes
    0.14
     Blanch
    0.14
    Act Density 0.586%

    No Known Activations