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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming classes and objects

    oai_token-act-pair · gpt-3.5-turbo

    references to programming classes and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.76
    andum
    -0.69
     mammoth
    -0.69
    Ö
    -0.68
    hiba
    -0.66
    STON
    -0.65
     wrought
    -0.65
    vernment
    -0.65
     usher
    -0.64
    yssey
    -0.63
    POSITIVE LOGITS
    ifier
    1.18
    ifications
    1.17
    ifies
    1.12
    ifiers
    1.11
    path
    1.00
    ification
    1.00
    ifying
    1.00
    classes
    0.97
    ifiable
    0.91
    ified
    0.91
    Act Density 0.017%

    No Known Activations