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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions, particularly related to distress and joy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    telser
    -0.59
     Himo
    -0.57
    apimachinery
    -0.56
    addPreferredGap
    -0.56
     '\\;'
    -0.55
    ebbe
    -0.54
     cương
    -0.52
     protoimpl
    -0.52
     élevés
    -0.52
    __()
    -0.51
    POSITIVE LOGITS
     loudly
    0.94
     louder
    0.86
     loudest
    0.86
     aloud
    0.84
     loud
    0.72
     uncontrol
    0.70
     hyster
    0.64
     softly
    0.62
     obsc
    0.61
     inwardly
    0.60
    Act Density 0.192%

    No Known Activations