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

    Neuronpedia

    INDEX
    Explanations

    Strong emotional expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'f'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.63
     thereto
    -0.61
    BuyableInstoreAndOnline
    -0.59
     sponsors
    -0.56
    many
    -0.55
     termin
    -0.55
     Ri
    -0.55
    Correct
    -0.53
    MENT
    -0.53
     compet
    -0.53
    POSITIVE LOGITS
    iddler
    1.14
    avour
    1.14
    ruits
    1.14
    ucking
    1.13
    lesh
    1.12
    licks
    1.09
    ication
    1.08
    ingers
    1.08
    iltration
    1.06
    ractions
    1.06
    Act Density 0.033%

    No Known Activations