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

    Neuronpedia

    INDEX
    Explanations

    instances of statistical analyses or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RITE
    -0.17
    ality
    -0.16
    ubo
    -0.16
    uba
    -0.16
     vic
    -0.16
    Vict
    -0.15
    _succ
    -0.14
    oba
    -0.14
    pler
    -0.14
    neas
    -0.14
    POSITIVE LOGITS
    feld
    0.16
    ardon
    0.16
     ifndef
    0.15
    δηÏĤ
    0.14
    /umd
    0.14
    ÑģÑĥ
    0.14
    ktop
    0.14
    ONGL
    0.14
    JE
    0.14
    olutely
    0.13
    Act Density 0.061%

    No Known Activations