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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pleasant
    -0.16
     Kushner
    -0.15
    Ä©
    -0.14
    lemen
    -0.14
    ins
    -0.13
     scope
    -0.13
    amm
    -0.13
     Citizens
    -0.13
    iff
    -0.13
    nit
    -0.13
    POSITIVE LOGITS
     interest
    0.19
     visita
    0.18
    apult
    0.17
    жд
    0.17
    join
    0.15
    corp
    0.15
     visiting
    0.15
    feedback
    0.15
     interes
    0.15
     visit
    0.15
    Act Density 0.024%

    No Known Activations