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

    Neuronpedia

    INDEX
    Explanations

    names, particularly last names, with varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ady", indicating female names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ational
    -0.95
    unci
    -0.74
    ardless
    -0.74
    bidden
    -0.71
    ingen
    -0.71
    falls
    -0.71
    osion
    -0.70
    ayers
    -0.68
    uring
    -0.68
    olation
    -0.67
    POSITIVE LOGITS
    rov
    0.98
    tsky
    0.82
    ptoms
    0.76
    rocal
    0.76
    ng
    0.73
    hawk
    0.72
    bilt
    0.72
    mbol
    0.72
    cade
    0.70
    hawks
    0.67
    Act Density 0.040%

    No Known Activations