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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives or compliments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Achieve
    -0.72
    osate
    -0.71
     cite
    -0.70
    icipated
    -0.68
    irm
    -0.68
     undertook
    -0.67
    ilst
    -0.67
    iates
    -0.66
     Deter
    -0.65
     Sources
    -0.65
    POSITIVE LOGITS
     gonna
    1.29
     definitely
    1.11
    nt
    1.08
     probably
    1.00
     kinda
    0.95
     fucked
    0.94
     awesome
    0.93
     amazing
    0.91
     supposed
    0.89
     pretty
    0.88
    Act Density 0.749%

    No Known Activations