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

    Neuronpedia

    INDEX
    Explanations

    mentions of praise and positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Symbol
    -0.15
     Accepted
    -0.14
    wang
    -0.14
     ARGS
    -0.14
    Symbol
    -0.14
    ellig
    -0.14
    ina
    -0.13
    _WARNING
    -0.13
    trad
    -0.13
     اÙĦرÙħ
    -0.13
    POSITIVE LOGITS
     praise
    0.38
     compliment
    0.37
     complement
    0.35
     praises
    0.32
     glowing
    0.32
     compliments
    0.32
     complimentary
    0.30
     praising
    0.29
     rave
    0.29
     comple
    0.28
    Act Density 0.243%

    No Known Activations