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

    Neuronpedia

    INDEX
    Explanations

    instances of discussions or threads that indicate a starting point in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aroo
    -0.16
    /goto
    -0.15
    óm
    -0.15
     Independence
    -0.14
    airy
    -0.14
    swick
    -0.14
    _portal
    -0.14
    à¹īà¸Ńà¸Ļ
    -0.14
    mach
    -0.14
    endl
    -0.14
    POSITIVE LOGITS
    yr
    0.16
    Äĥm
    0.15
    ContentAlignment
    0.14
    _deps
    0.14
    tains
    0.14
    aba
    0.14
    _Template
    0.13
     Goodman
    0.13
    æĶ¯
    0.13
    nga
    0.13
    Act Density 0.003%

    No Known Activations