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

    Neuronpedia

    INDEX
    Explanations

    numeric values in a statistical or data-driven context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è³¢
    -0.16
     betr
    -0.16
     GRE
    -0.15
    alent
    -0.15
     Hack
    -0.15
    s
    -0.14
    ANTE
    -0.14
    ech
    -0.14
     Wax
    -0.14
     HACK
    -0.13
    POSITIVE LOGITS
    roperty
    0.17
    emoc
    0.16
     Jeh
    0.15
    illez
    0.14
    ãĥ¼ãĥł
    0.14
    688
    0.14
    PERT
    0.14
    飾
    0.14
    perty
    0.13
    acco
    0.13
    Act Density 0.223%

    No Known Activations