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

    Neuronpedia

    INDEX
    Explanations

    adjectives denoting strong positive emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of amazement or admiration regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erent
    -0.88
    agle
    -0.74
    eeper
    -0.73
    eret
    -0.71
    odox
    -0.71
    eper
    -0.71
    enhagen
    -0.69
    veland
    -0.68
     stale
    -0.67
    istant
    -0.66
    POSITIVE LOGITS
     ecstasy
    0.76
     pandemonium
    0.74
     Beaut
    0.73
     proportions
    0.73
     unbeliev
    0.73
    Beaut
    0.70
     Beasts
    0.68
     feats
    0.68
     è£ıç
    0.67
    Merit
    0.66
    Act Density 0.587%

    No Known Activations