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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and social obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    “……”
    -0.43
    ・・・」
    -0.43
    ñores
    -0.42
     peor
    -0.41
     unbelievable
    -0.40
     FAILED
    -0.39
    writeFileSync
    -0.39
    ……」
    -0.39
     fucking
    -0.39
    ？】
    -0.38
    POSITIVE LOGITS
     :)
    1.51
     (:
    1.35
     :)</
    1.23
     <
    1.22
     :))
    1.21
     :*
    1.20
     =)
    1.20
    :)
    1.17
     ^_^
    1.17
     :]
    1.16
    Act Density 0.447%

    No Known Activations