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

    Neuronpedia

    INDEX
    Explanations

    phrases containing German words or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and repetitions of the letter 'b'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Magikarp
    -0.66
    eer
    -0.61
     Lear
    -0.58
     suscept
    -0.57
     Enix
    -0.57
     insidious
    -0.57
     Fenrir
    -0.57
     NTS
    -0.56
     Gon
    -0.55
     spect
    -0.55
    POSITIVE LOGITS
    ruary
    1.21
    rief
    1.20
    attery
    1.17
    untu
    1.16
    rities
    1.15
    odies
    1.12
    abies
    1.12
    esides
    1.11
    amboo
    1.09
    ureau
    1.09
    Act Density 0.054%

    No Known Activations