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

    Neuronpedia

    INDEX
    Explanations

    emotions and feelings associated with experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udies
    -0.17
    leground
    -0.16
    bes
    -0.16
    inae
    -0.16
    ndx
    -0.15
    rik
    -0.14
    sbin
    -0.14
    ıģı
    -0.14
    ortal
    -0.13
    plorer
    -0.13
    POSITIVE LOGITS
     having
    0.31
     being
    0.28
     hearing
    0.28
     knowing
    0.28
    having
    0.23
     seeing
    0.22
     watching
    0.22
     actually
    0.21
     realizing
    0.21
    being
    0.21
    Act Density 0.124%

    No Known Activations