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

    Neuronpedia

    INDEX
    Explanations

    phrase that start with "Not" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating something is less than expected or average

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etimes
    -0.82
    TIME
    -0.81
    aughs
    -0.72
    éĹĺ
    -0.71
    Ĥİ
    -0.70
    cki
    -0.67
    £ı
    -0.66
    llah
    -0.66
    metry
    -0.64
    WAY
    -0.63
    POSITIVE LOGITS
     terribly
    1.25
     overly
    1.25
     flashy
    1.24
     overpower
    1.16
    icably
    1.08
     terrible
    1.08
     necessarily
    1.06
     bad
    1.05
     particularly
    1.03
     excessively
    1.00
    Act Density 0.151%

    No Known Activations