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

    Neuronpedia

    INDEX
    Explanations

    negations and qualifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YNAM
    -0.16
     Lyons
    -0.15
    åģ
    -0.15
    uren
    -0.15
    aside
    -0.14
     thang
    -0.14
    berger
    -0.14
     Verd
    -0.14
     onBind
    -0.14
    OrCreate
    -0.14
    POSITIVE LOGITS
     outright
    0.17
    ardy
    0.16
    ForKey
    0.15
    akk
    0.15
     certainly
    0.15
     ultimately
    0.15
     not
    0.15
     ultimate
    0.15
    ucs
    0.15
    udo
    0.15
    Act Density 0.079%

    No Known Activations