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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration and criticism regarding relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    érica
    -0.15
     Nag
    -0.15
     suspects
    -0.15
    chet
    -0.14
    airo
    -0.14
     Holland
    -0.14
    ospace
    -0.13
    sel
    -0.13
    avel
    -0.13
     ins
    -0.13
    POSITIVE LOGITS
     simples
    0.20
     simple
    0.19
    .Simple
    0.18
     Simple
    0.18
     SIMPLE
    0.18
    ôi
    0.18
    amenti
    0.17
    Simple
    0.17
    simple
    0.17
    FileSync
    0.16
    Act Density 0.203%

    No Known Activations