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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to causal relationships or emphasizing the natural or logical connection between events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express inevitability or natural consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.78
    agall
    -0.69
    enary
    -0.68
    abase
    -0.67
    yet
    -0.66
    tein
    -0.66
    burgh
    -0.66
    ultz
    -0.65
    raph
    -0.64
    berman
    -0.64
    POSITIVE LOGITS
     grav
    0.82
     ensued
    0.81
     occurring
    0.77
     attracted
    0.75
     delighted
    0.75
     arises
    0.74
     provoked
    0.73
     accompanies
    0.72
     disple
    0.70
     fascinated
    0.69
    Act Density 0.089%

    No Known Activations