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

    Neuronpedia

    INDEX
    Explanations

    non-standard text or formatting elements, possibly related to coding or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecimal
    -0.15
     Wan
    -0.15
    dg
    -0.15
    esti
    -0.15
    \Base
    -0.14
    mainwindow
    -0.14
    ató
    -0.14
     priv
    -0.14
     Nachricht
    -0.14
     CAB
    -0.14
    POSITIVE LOGITS
    pb
    0.17
     pb
    0.16
    oa
    0.16
     Brennan
    0.16
    oons
    0.14
     Haram
    0.14
    IVE
    0.14
    ve
    0.13
    oon
    0.13
    ua
    0.13
    Act Density 0.001%

    No Known Activations