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

    Neuronpedia

    INDEX
    Explanations

    references to reports and rebuttals in a discussion or commentary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñana
    -0.18
    163
    -0.16
    ìłķ
    -0.16
     Nova
    -0.15
    éal
    -0.15
    563
    -0.14
    TTY
    -0.14
     silk
    -0.14
     Silk
    -0.14
     Jenkins
    -0.14
    POSITIVE LOGITS
     below
    0.16
    oulos
    0.16
     abaixo
    0.15
    bedo
    0.15
    -IN
    0.15
    imizi
    0.15
    UNUSED
    0.15
    Below
    0.15
     Below
    0.15
    vyk
    0.14
    Act Density 0.099%

    No Known Activations