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

    Neuronpedia

    INDEX
    Explanations

    dates and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brero
    -0.17
    ero
    -0.16
    729
    -0.15
    ublik
    -0.15
    nemonic
    -0.15
    eness
    -0.15
    /legal
    -0.14
    983
    -0.14
    imes
    -0.14
    era
    -0.14
    POSITIVE LOGITS
    ndef
    0.15
    zdy
    0.15
    Äįer
    0.14
    nid
    0.14
    rd
    0.14
    _tgt
    0.13
    anches
    0.13
    "><!--
    0.13
     Dagger
    0.13
    likelihood
    0.13
    Act Density 0.023%

    No Known Activations