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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ude
    -0.15
     Circular
    -0.15
     Pulse
    -0.15
    raz
    -0.14
    گاÙĩ
    -0.14
     fronts
    -0.14
    gh
    -0.14
    enden
    -0.14
    anka
    -0.14
    ika
    -0.13
    POSITIVE LOGITS
    jom
    0.16
    BYTES
    0.15
    odzi
    0.15
     Rud
    0.14
    esub
    0.14
    olas
    0.14
    ään
    0.14
    $MESS
    0.13
    ë¥
    0.13
    ãģ£ãģ¦ãģįãģŁ
    0.13
    Act Density 0.056%

    No Known Activations