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

    Neuronpedia

    INDEX
    Explanations

    references to personal or collective pronouns, highlighting the sense of inclusion or identity in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.63
     Waller
    -0.57
     ftate
    -0.57
     houſe
    -0.56
    ikke
    -0.55
     Darío
    -0.54
     ſch
    -0.54
     galeria
    -0.53
    gestone
    -0.53
     Sepp
    -0.52
    POSITIVE LOGITS
    expandindo
    0.87
    InjectAttribute
    0.72
     ModelExpression
    0.71
    хьтан
    0.66
    aarrggbb
    0.65
     ویکی‌پدی
    0.65
     kasarigan
    0.64
    +#+#
    0.63
    ngdoc
    0.63
    Jereo
    0.63
    Act Density 0.158%

    No Known Activations