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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating suggestions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.16
    asco
    -0.15
    év
    -0.15
    illez
    -0.14
    ìĬ¤íĦ°
    -0.14
    uml
    -0.14
    ãĥ¬ãĤ¤
    -0.14
    vez
    -0.14
    sembler
    -0.14
    anzeigen
    -0.14
    POSITIVE LOGITS
    owie
    0.17
    ande
    0.17
    ucas
    0.16
    rome
    0.15
    eb
    0.15
     SJ
    0.14
     mee
    0.14
    asper
    0.14
     Kare
    0.13
     Tig
    0.13
    Act Density 0.019%

    No Known Activations