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

    Neuronpedia

    INDEX
    Explanations

    playful or fanciful suffixes in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leine
    -0.16
    iesz
    -0.16
    iyan
    -0.16
    ̧
    -0.15
    quential
    -0.15
    ascript
    -0.15
    uya
    -0.15
    asury
    -0.15
    GenericType
    -0.14
    bsite
    -0.14
    POSITIVE LOGITS
    lic
    0.26
    kins
    0.17
    ism
    0.17
    -go
    0.17
    mania
    0.17
    -vous
    0.16
    ama
    0.16
    grams
    0.16
    ville
    0.16
    ear
    0.15
    Act Density 0.091%

    No Known Activations