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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'e'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.77
    lime
    -0.74
    anova
    -0.73
    iets
    -0.71
    itational
    -0.69
    irtual
    -0.69
     ESA
    -0.68
    rooms
    -0.68
     glim
    -0.67
    s
    -0.67
    POSITIVE LOGITS
    lements
    1.31
    cki
    1.10
    gger
    1.08
    zza
    1.07
    ck
    1.05
    agle
    1.05
    cker
    1.04
    agles
    1.03
    ld
    1.01
    gan
    0.98
    Act Density 0.043%

    No Known Activations