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

    Neuronpedia

    INDEX
    Explanations

    positive or affirmative expressions and strong emotional sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cha
    -0.17
    ยว
    -0.16
    otti
    -0.16
     takson
    -0.15
    arak
    -0.15
    urette
    -0.15
     ruk
    -0.15
    atori
    -0.14
    ิว
    -0.14
    .pa
    -0.14
    POSITIVE LOGITS
    tron
    0.16
    uin
    0.15
    usz
    0.15
    osit
    0.15
     among
    0.14
     barr
    0.14
    mapped
    0.14
    μει
    0.14
     Avg
    0.14
    phia
    0.14
    Act Density 0.003%

    No Known Activations