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

    Neuronpedia

    INDEX
    Explanations

    conjunctions followed by interjections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of realization or emphasis, often introducing statements or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.81
    arij
    -0.78
    arov
    -0.75
    resso
    -0.75
    -+-+
    -0.75
    Roaming
    -0.74
    İĭ
    -0.74
    alion
    -0.73
    actionDate
    -0.72
    ascript
    -0.71
    POSITIVE LOGITS
     goodness
    0.97
     heavens
    0.97
     yes
    0.96
     yeah
    0.95
     dear
    0.94
     Merlin
    0.88
     GOD
    0.86
     sorry
    0.85
     wait
    0.85
     god
    0.85
    Act Density 0.037%

    No Known Activations