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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism or questions about societal norms and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hits
    -0.15
    Hits
    -0.14
    hit
    -0.14
    dater
    -0.14
    okino
    -0.14
    ificent
    -0.14
     hits
    -0.14
    mdl
    -0.14
    estion
    -0.14
    oader
    -0.14
    POSITIVE LOGITS
    ess
    0.14
    æĭ¥
    0.14
     ÃĩaÄŁ
    0.14
    .collider
    0.14
    ForResource
    0.14
    Ãło
    0.13
    нÑĸÑĪ
    0.13
     SCIP
    0.13
    lette
    0.13
    CustomAttributes
    0.13
    Act Density 0.046%

    No Known Activations