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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states, particularly feelings of happiness and satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoS
    -0.76
    artifacts
    -0.72
    heat
    -0.71
    sites
    -0.71
    method
    -0.69
    arin
    -0.68
    ents
    -0.68
    ngth
    -0.67
    Downloadha
    -0.67
    ciplinary
    -0.67
    POSITIVE LOGITS
    joy
    0.90
    vale
    0.80
     happy
    0.80
     birthday
    0.78
    istic
    0.72
     âĶľ
    0.72
     Meal
    0.70
     endings
    0.65
    iliate
    0.65
    omas
    0.65
    Act Density 0.021%

    No Known Activations