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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to pricing or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    380
    -0.17
    437
    -0.16
    abcdefghijklmnop
    -0.16
    anton
    -0.14
    373
    -0.14
     and
    -0.14
    389
    -0.14
    marvin
    -0.14
    667
    -0.13
    wnd
    -0.13
    POSITIVE LOGITS
    /or
    0.25
    /OR
    0.18
    quot
    0.17
    rag
    0.16
    orra
    0.16
    rog
    0.16
    ни
    0.15
    atak
    0.15
    ience
    0.15
     Went
    0.13
    Act Density 0.050%

    No Known Activations