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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic courses, events, or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords and terms related to programming or coding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.81
    20439
    -0.78
     Debor
    -0.69
    ocumented
    -0.69
    åŃ
    -0.68
    quartered
    -0.66
    lihood
    -0.65
    jas
    -0.63
    credit
    -0.62
    iences
    -0.62
    POSITIVE LOGITS
     CoC
    0.76
    +
    0.64
     +
    0.63
     vs
    0.61
     ÃĹ
    0.61
    ++
    0.59
    ²
    0.59
     SLI
    0.59
    oslov
    0.58
    âĢ²
    0.58
    Act Density 0.226%

    No Known Activations