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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to computing and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INES
    -0.16
    ATUS
    -0.15
    orizontal
    -0.15
    ordion
    -0.15
    ocks
    -0.14
    xea
    -0.14
    atus
    -0.14
    à¹ĩว
    -0.14
    ines
    -0.14
    ç³»
    -0.13
    POSITIVE LOGITS
     mechanism
    0.16
    stad
    0.14
    defer
    0.14
    borg
    0.14
    tu
    0.14
    olerance
    0.14
    _ASM
    0.13
    оло
    0.13
    ulerAngles
    0.13
     cred
    0.13
    Act Density 0.120%

    No Known Activations