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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating variety or diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slut
    -0.16
    ume
    -0.15
    own
    -0.15
    IED
    -0.14
    λε
    -0.14
    au
    -0.14
    NIC
    -0.13
    iaux
    -0.13
    ughter
    -0.13
    лÑĥги
    -0.13
    POSITIVE LOGITS
    alli
    0.17
    .checkNotNull
    0.14
    icast
    0.14
    ModelProperty
    0.13
     Hob
    0.13
     Garland
    0.13
    eteria
    0.13
    fers
    0.13
    å¿Ĺ
    0.13
     vòng
    0.13
    Act Density 0.013%

    No Known Activations