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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a critical assessment of situations or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lox
    -0.18
    679
    -0.16
    Synopsis
    -0.16
    enko
    -0.15
    andard
    -0.15
    AFX
    -0.14
     Kaplan
    -0.14
     Fil
    -0.13
    ãĤ¤ãĥī
    -0.13
    Bearer
    -0.13
    POSITIVE LOGITS
    ROTO
    0.15
    errupt
    0.15
    ishops
    0.14
    \uff
    0.14
     çķ
    0.14
    áty
    0.14
    elik
    0.14
    .ImageAlign
    0.14
    erti
    0.13
    /cms
    0.13
    Act Density 0.031%

    No Known Activations