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

    Neuronpedia

    INDEX
    Explanations

    references to various programs or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccak
    -0.15
    ãģ©
    -0.15
    ãĥªãĥ¼
    -0.14
    iley
    -0.14
    ienne
    -0.14
    odon
    -0.14
    rar
    -0.14
    gro
    -0.14
    onda
    -0.14
    pard
    -0.14
    POSITIVE LOGITS
    åĦĢ
    0.16
    ices
    0.16
    och
    0.15
    teri
    0.14
    olumes
    0.14
    uche
    0.14
     BET
    0.13
    ichte
    0.13
    DMI
    0.13
    ues
    0.13
    Act Density 0.015%

    No Known Activations