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

    Neuronpedia

    INDEX
    Explanations

    references to captions or captioning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pcodes
    -0.15
    ppelin
    -0.15
    ucht
    -0.15
    rought
    -0.14
    vary
    -0.14
    enberg
    -0.14
    cka
    -0.14
    elder
    -0.14
    mana
    -0.14
    .qq
    -0.14
    POSITIVE LOGITS
    obus
    0.16
    itsu
    0.16
    ing
    0.15
    iqué
    0.14
     cock
    0.14
    905
    0.14
    esso
    0.14
    icker
    0.14
    rada
    0.14
    CEPT
    0.13
    Act Density 0.003%

    No Known Activations