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

    Neuronpedia

    INDEX
    Explanations

    references to organized discussions or presentations, such as panels and meetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.15
    ROM
    -0.14
    ething
    -0.14
    enko
    -0.14
    AMAGE
    -0.14
    erk
    -0.13
    /manage
    -0.13
    erken
    -0.13
    urum
    -0.13
    rych
    -0.13
    POSITIVE LOGITS
    tea
    0.17
    ãĤ¿ãĥ³
    0.16
    asca
    0.15
    ews
    0.15
     Eh
    0.15
    mvc
    0.15
    ãĥ©ãĤ¹
    0.15
    afx
    0.15
    ductor
    0.14
    terra
    0.14
    Act Density 0.149%

    No Known Activations