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

    Neuronpedia

    INDEX
    Explanations

    references to concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUR
    -0.17
    deer
    -0.17
    coming
    -0.17
    adow
    -0.16
    eeper
    -0.16
    alnız
    -0.15
    agi
    -0.15
    aces
    -0.15
    ity
    -0.15
    ings
    -0.15
    POSITIVE LOGITS
    ually
    0.51
    ual
    0.40
    UAL
    0.30
    uality
    0.26
    uali
    0.26
    tual
    0.25
    ively
    0.24
    uele
    0.22
    uale
    0.22
    ors
    0.20
    Act Density 0.022%

    No Known Activations