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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of specific suffixes in verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iastical
    -0.55
     Reſ
    -0.55
    ioare
    -0.54
     reafon
    -0.54
     poffible
    -0.54
    verticalLayout
    -0.53
    osidad
    -0.53
     fubject
    -0.53
     reaſon
    -0.52
     ſtate
    -0.52
    POSITIVE LOGITS
    ando
    4.07
    ANDO
    3.19
    rando
    1.47
    cando
    1.44
    andos
    1.42
    mando
    1.29
    endo
    1.27
    andola
    1.23
    izando
    1.20
    zando
    1.20
    Act Density 0.027%

    No Known Activations