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

    Neuronpedia

    INDEX
    Explanations

    words related to visual design and typography

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discernment and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wraps
    -0.66
     Babe
    -0.65
     prom
    -0.65
     UT
    -0.64
    Ak
    -0.62
     Pax
    -0.62
     slavery
    -0.62
    ax
    -0.61
     Supporters
    -0.60
     Agg
    -0.59
    POSITIVE LOGITS
    erning
    2.76
     discern
    2.32
    omever
    1.32
     percept
    1.18
     capitals
    1.14
    aspers
    1.14
     Editors
    1.12
     decipher
    1.02
     glean
    0.95
    lear
    0.89
    Act Density 0.077%

    No Known Activations