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

    Neuronpedia

    INDEX
    Explanations

    expressions related to credibility and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    re
    -0.15
    enna
    -0.15
    ·
    -0.15
    ´
    -0.14
    _PAD
    -0.14
    2
    -0.14
    AA
    -0.14
    jay
    -0.14
    aw
    -0.14
     eccentric
    -0.14
    POSITIVE LOGITS
    ragon
    0.17
    ToWorld
    0.17
    /mainwindow
    0.17
    å´İ
    0.16
    etsk
    0.16
    .Generated
    0.16
    xbb
    0.16
     Obr
    0.16
    sdk
    0.16
    .scalablytyped
    0.16
    Act Density 0.009%

    No Known Activations