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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions or endings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a conclusion or culmination of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     congratulated
    -0.76
     Alone
    -0.66
     Architecture
    -0.65
    adeon
    -0.63
     Phant
    -0.62
     Divinity
    -0.62
     Supports
    -0.62
     Donation
    -0.62
     elig
    -0.59
     endeav
    -0.59
    POSITIVE LOGITS
    emer
    0.73
    escal
    0.69
    erenn
    0.65
     unbeliev
    0.63
     bear
    0.63
     abrupt
    0.62
    acerb
    0.62
     sharper
    0.62
     jurisd
    0.61
    tw
    0.61
    Act Density 0.332%

    No Known Activations