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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Overview"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isha
    -0.17
    770
    -0.16
    Ãłn
    -0.16
    abyrin
    -0.16
    -exclusive
    -0.15
    lear
    -0.15
    ppo
    -0.15
    ána
    -0.14
    utive
    -0.14
    jerne
    -0.14
    POSITIVE LOGITS
    fec
    0.16
    rij
    0.15
    οÏħ
    0.14
     sequ
    0.14
     blue
    0.14
     BLUE
    0.14
    entes
    0.14
    ople
    0.13
    reak
    0.13
     mod
    0.13
    Act Density 0.005%

    No Known Activations