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

    Neuronpedia

    INDEX
    Explanations

    references to metaphorical language and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lator
    -0.16
    ervals
    -0.15
    oll
    -0.15
    .rf
    -0.14
    brush
    -0.14
    ering
    -0.14
     san
    -0.14
    iba
    -0.14
    rado
    -0.13
    ámara
    -0.13
    POSITIVE LOGITS
    -Clause
    0.15
    quo
    0.14
    iminal
    0.14
    PerPixel
    0.14
    ichel
    0.14
    _blocked
    0.14
    celik
    0.13
    AXB
    0.13
     Sof
    0.13
    quette
    0.13
    Act Density 0.023%

    No Known Activations