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

    Neuronpedia

    INDEX
    Explanations

    words related to enrollment or registration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enrollment and encryption processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ---------
    -0.68
    STEM
    -0.65
     afore
    -0.65
    >>\
    -0.64
    existent
    -0.64
    REDACTED
    -0.64
    ItemThumbnailImage
    -0.60
     Sisters
    -0.60
     Elves
    -0.59
    ----------------
    -0.59
    POSITIVE LOGITS
    ing
    1.65
    ments
    1.39
    ions
    1.27
    ings
    1.10
    ively
    1.09
    resses
    1.09
    abilia
    1.06
    ations
    1.03
    acles
    1.03
    ors
    1.02
    Act Density 0.086%

    No Known Activations