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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or positive sentiment in relation to events or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kadang
    -0.65
     sometimes
    -0.62
     soms
    -0.60
     parfois
    -0.59
     Sometimes
    -0.58
     bazen
    -0.58
    sometimes
    -0.57
     иногда
    -0.54
    cobra
    -0.54
     manchmal
    -0.54
    POSITIVE LOGITS
    Excited
    0.98
     excited
    0.97
     Excited
    0.93
     thrilled
    0.92
    Joining
    0.88
     delighted
    0.86
     joining
    0.82
     Joining
    0.77
    SequentialGroup
    0.75
     joins
    0.75
    Act Density 0.104%

    No Known Activations