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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific word 'Sub' with either a numerical suffix or a specific context

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of the term "Sub" followed by a number, indicating a focus on a specific topic or concept related to "Sub."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĽ
    -0.84
    çİĭ
    -0.81
     GOODMAN
    -0.80
    OHN
    -0.80
     Papers
    -0.76
     Dol
    -0.76
    assetsadobe
    -0.76
    çĦ
    -0.75
    IER
    -0.75
    OPLE
    -0.75
    POSITIVE LOGITS
    sequent
    1.40
    sequently
    1.40
    mitted
    1.27
    jug
    1.22
    marine
    1.16
    missive
    1.15
    stantial
    1.14
    ordinate
    1.14
    mitting
    1.09
    izoph
    1.05
    Act Density 0.008%

    No Known Activations