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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odule
    -0.16
    foods
    -0.16
    isia
    -0.15
    ADDE
    -0.15
    utin
    -0.14
    _nat
    -0.14
    essaging
    -0.14
    ãĥ©ãĥ³ãĥī
    -0.13
    531
    -0.13
    appa
    -0.13
    POSITIVE LOGITS
    _wf
    0.15
    ely
    0.15
     propag
    0.14
    axed
    0.14
    ked
    0.14
    ardon
    0.13
    elop
    0.13
    Propagation
    0.13
     hall
    0.13
    -to
    0.13
    Act Density 0.038%

    No Known Activations