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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional reactions and interactions in narratives and communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inn
    -0.15
    ccount
    -0.14
    ering
    -0.14
    зÑĮ
    -0.14
    nda
    -0.14
    ÙĪØ«
    -0.14
    декÑģ
    -0.14
    kili
    -0.14
    hani
    -0.13
     CHE
    -0.13
    POSITIVE LOGITS
    oppers
    0.17
    ustom
    0.17
     bites
    0.16
    rott
    0.16
    astically
    0.16
     ########.
    0.15
     bite
    0.15
     Punch
    0.15
    æ¤į
    0.14
    ooks
    0.14
    Act Density 0.845%

    No Known Activations