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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific characters or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elif
    -0.17
    lish
    -0.16
    209
    -0.15
    ampie
    -0.15
    sis
    -0.15
    alc
    -0.14
    loating
    -0.14
     shadow
    -0.14
     Möglich
    -0.14
     Household
    -0.14
    POSITIVE LOGITS
    ohn
    0.23
    agers
    0.22
    ese
    0.21
    age
    0.21
    AGER
    0.20
    izens
    0.20
    kw
    0.19
    agen
    0.19
    ern
    0.19
    andle
    0.18
    Act Density 0.009%

    No Known Activations