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

    Neuronpedia

    INDEX
    Explanations

    frequent personal pronouns and expressions of first-person perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decorativas
    -0.65
     sauvages
    -0.64
     prêtres
    -0.63
    PathVariable
    -0.61
    brainly
    -0.60
    AnchorStyles
    -0.59
     plastiques
    -0.57
     comportements
    -0.57
     brilh
    -0.55
     tóxic
    -0.55
    POSITIVE LOGITS
     hadn
    0.68
    __':
    0.64
     wouldn
    0.62
     didn
    0.57
    )");
    0.55
    __":
    0.52
    }));
    0.52
     BrowserModule
    0.51
    kus
    0.51
     haven
    0.51
    Act Density 0.234%

    No Known Activations