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

    Neuronpedia

    INDEX
    Explanations

    references to components or elements of a system or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rror
    -0.16
    han
    -0.16
    nder
    -0.15
    rn
    -0.15
    bic
    -0.15
    ngth
    -0.15
    pty
    -0.15
    den
    -0.15
    hist
    -0.14
    uvre
    -0.14
    POSITIVE LOGITS
    isans
    0.25
    aking
    0.25
    akers
    0.25
    iers
    0.21
     our
    0.21
    ioned
    0.20
    uring
    0.20
    aker
    0.19
    f
    0.19
    -owner
    0.19
    Act Density 0.042%

    No Known Activations