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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assertive statements

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various forms and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilst
    -0.72
     Achieve
    -0.71
    iates
    -0.71
    udeau
    -0.68
    atives
    -0.66
     accuses
    -0.65
    ipient
    -0.63
    osate
    -0.63
     Sources
    -0.62
     alleges
    -0.61
    POSITIVE LOGITS
     gonna
    1.30
    nt
    1.15
     ALWAYS
    1.12
     definitely
    1.06
     always
    0.97
    senal
    0.96
     probably
    0.95
     kinda
    0.95
     amazing
    0.92
     supposed
    0.91
    Act Density 0.556%

    No Known Activations