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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Or" and method overrides in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agen
    -0.49
     agents
    -0.47
     nakalista
    -0.47
     conci
    -0.46
     fus
    -0.45
    Hentet
    -0.45
    ']."
    -0.45
     exh
    -0.45
     scape
    -0.45
     Conci
    -0.44
    POSITIVE LOGITS
    httphttps
    0.60
    Online
    0.53
     zijne
    0.52
     graça
    0.52
    doors
    0.52
     amitié
    0.51
     drzwi
    0.47
     íntimo
    0.46
     vectorielles
    0.46
     rodzic
    0.46
    Act Density 0.165%

    No Known Activations