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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "I" and other personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.15
    inox
    -0.15
    orno
    -0.14
    erve
    -0.14
     corr
    -0.14
    è´¹
    -0.14
    eren
    -0.14
    figcaption
    -0.14
    gateway
    -0.13
    otec
    -0.13
    POSITIVE LOGITS
    uyen
    0.16
    ierge
    0.16
    umber
    0.16
    completed
    0.15
    apons
    0.15
    _utilities
    0.15
    crest
    0.14
    addir
    0.14
    viso
    0.14
    Handled
    0.14
    Act Density 0.001%

    No Known Activations