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

    Neuronpedia

    INDEX
    Explanations

    specific terms or phrases indicative of technical specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caff
    -0.17
     Podesta
    -0.14
    ullen
    -0.13
    lacak
    -0.13
    puted
    -0.13
     Mitchell
    -0.13
    aris
    -0.13
    ãĤ¦ãĥĪ
    -0.13
    Äįek
    -0.13
     Penn
    -0.13
    POSITIVE LOGITS
    erman
    0.18
    erate
    0.16
    er
    0.15
     uncert
    0.15
    lobals
    0.14
    edi
    0.14
    ews
    0.14
    ic
    0.14
    erie
    0.14
    ignon
    0.13
    Act Density 0.008%

    No Known Activations