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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continúas
    -0.63
    windowFixed
    -0.63
     linkovi
    -0.62
     continuant
    -0.62
     OMITBAD
    -0.58
    ----+
    -0.58
     malheureusement
    -0.56
     unfortunately
    -0.56
    brigens
    -0.56
     Normdatei
    -0.56
    POSITIVE LOGITS
     holy
    1.15
     Holy
    1.08
    Holy
    1.05
    holy
    1.02
     WTF
    0.99
     Wtf
    0.98
     HOLY
    0.97
     OMG
    0.96
     omg
    0.94
     wtf
    0.93
    Act Density 0.191%

    No Known Activations