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

    Neuronpedia

    INDEX
    Explanations

    instances of specific letters or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amazon
    -0.17
    -se
    -0.16
     pa
    -0.15
    avia
    -0.15
     Cong
    -0.15
     perv
    -0.15
    kil
    -0.15
    ught
    -0.14
    undry
    -0.14
    iei
    -0.14
    POSITIVE LOGITS
    apos
    0.21
    god
    0.19
    adr
    0.19
    avr
    0.18
    elo
    0.18
    bir
    0.18
    grad
    0.18
    unan
    0.18
    nan
    0.17
    idar
    0.17
    Act Density 0.002%

    No Known Activations