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

    Neuronpedia

    INDEX
    Explanations

    words related to academic discussions and expert opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lue
    -0.15
    ceived
    -0.15
    uhe
    -0.15
    ahead
    -0.14
    ÙĪÙĦا
    -0.14
     Reputation
    -0.14
     odp
    -0.14
    omer
    -0.14
    (reinterpret
    -0.14
    wart
    -0.13
    POSITIVE LOGITS
     consensus
    0.26
     agree
    0.25
     agreement
    0.22
     agrees
    0.22
     agreed
    0.22
     unanim
    0.21
     debate
    0.21
     alike
    0.20
     united
    0.19
     tends
    0.19
    Act Density 0.116%

    No Known Activations