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

    Neuronpedia

    INDEX
    Explanations

    references to utility functions and utilities within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acho
    -0.19
    alam
    -0.17
    abwe
    -0.14
    imus
    -0.14
    actories
    -0.14
    eo
    -0.14
    NEY
    -0.14
    گرÛĮ
    -0.14
    agne
    -0.14
    iyon
    -0.14
    POSITIVE LOGITS
     Bits
    0.16
     tunnel
    0.15
     thirst
    0.14
     primarily
    0.14
     res
    0.13
     lax
    0.13
    :
    0.13
     spare
    0.13
    res
    0.13
     otherwise
    0.13
    Act Density 0.005%

    No Known Activations