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

    Neuronpedia

    INDEX
    Explanations

    suffixes indicative of adjectives or descriptive terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.48
    yi
    -0.34
    yy
    -0.34
    ye
    -0.32
    yr
    -0.30
    yd
    -0.30
    ya
    -0.30
    ing
    -0.30
    yyy
    -0.29
    yk
    -0.29
    POSITIVE LOGITS
    mp
    0.18
    MMdd
    0.18
    ler
    0.17
    rs
    0.16
    set
    0.16
    kánÃŃ
    0.16
    hra
    0.16
    ees
    0.16
    est
    0.15
    serie
    0.15
    Act Density 0.155%

    No Known Activations