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

    Neuronpedia

    INDEX
    Explanations

    the word "Before" indicating prior events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antar
    -0.15
    555
    -0.15
    æĦ
    -0.15
    inker
    -0.15
    ann
    -0.15
    лем
    -0.14
    lam
    -0.14
    uell
    -0.14
    adora
    -0.14
    blade
    -0.14
    POSITIVE LOGITS
    shima
    0.16
    onian
    0.15
    ör
    0.15
    Ģ
    0.15
    bidden
    0.15
    orthand
    0.15
    zug
    0.14
    ALER
    0.14
     Bols
    0.14
    lesen
    0.14
    Act Density 0.018%

    No Known Activations