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

    Neuronpedia

    INDEX
    Explanations

    bracketed pieces of text and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vale
    -0.16
    -Type
    -0.15
    erd
    -0.14
    olio
    -0.14
    rels
    -0.14
     Retro
    -0.13
    tone
    -0.13
    à¥Ĥष
    -0.13
    vida
    -0.13
    ĵåIJį
    -0.13
    POSITIVE LOGITS
     Shank
    0.16
     taper
    0.15
    ecided
    0.14
    Ùģت
    0.14
    ãĥ¼ãĥĨ
    0.14
    yles
    0.14
    avenport
    0.14
    achel
    0.14
    IENT
    0.13
     Saint
    0.13
    Act Density 0.002%

    No Known Activations