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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    fragments of text possibly related to online interactions or comments, focusing on user sentiment and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wedd
    -0.86
     estranged
    -0.77
     eighty
    -0.76
     enriched
    -0.76
     elevated
    -0.75
     enrolled
    -0.75
     exiled
    -0.75
    intendent
    -0.75
     fleeing
    -0.74
     enroll
    -0.73
    POSITIVE LOGITS
    Anyway
    1.35
    Example
    1.12
    Posted
    1.09
    Also
    1.08
    edit
    1.06
    Spoiler
    1.05
    EDIT
    1.04
     Anyway
    1.02
    Edit
    0.98
    Side
    0.98
    Act Density 0.468%

    No Known Activations