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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.60
    kinci
    -0.59
    setGravity
    -0.59
    Jae
    -0.58
     NSCoder
    -0.55
    instellungen
    -0.53
     parseFrom
    -0.51
     legale
    -0.51
    asker
    -0.50
     Gnade
    -0.49
    POSITIVE LOGITS
     excitement
    1.31
     excite
    1.26
     thrill
    1.14
     excites
    1.12
     Excited
    1.08
    excitation
    1.07
     excitation
    1.07
     excited
    1.05
     thrills
    1.05
    excited
    1.03
    Act Density 0.568%

    No Known Activations