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

    Neuronpedia

    INDEX
    Explanations

    emotions, particularly feelings of distress and shock, expressed by physical actions like crying, sighing, or showing confusion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional responses, particularly related to sadness and distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©Ł
    -0.67
     shady
    -0.64
    Fa
    -0.63
     favors
    -0.63
    oln
    -0.62
    akedown
    -0.62
    hod
    -0.61
    rf
    -0.60
    Ranked
    -0.60
     Practices
    -0.59
    POSITIVE LOGITS
     exclaim
    0.94
     hyster
    0.89
     disbelief
    0.86
     incred
    0.85
     recalling
    0.84
     tears
    0.84
     laughter
    0.80
     amaz
    0.80
     uncontroll
    0.78
     sob
    0.78
    Act Density 0.183%

    No Known Activations