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

    Neuronpedia

    INDEX
    Explanations

    terms related to publishing and publication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ides
    -0.15
    128
    -0.15
    lessly
    -0.14
    stadt
    -0.14
     Sanity
    -0.14
    209
    -0.14
     Stanley
    -0.14
    upon
    -0.14
     pitched
    -0.14
    -headed
    -0.14
    POSITIVE LOGITS
    (crate
    0.23
    ICATION
    0.22
    houses
    0.17
    ured
    0.17
    jabi
    0.17
    /export
    0.17
    typeid
    0.16
     Savage
    0.16
    itive
    0.15
     khoa
    0.15
    Act Density 0.038%

    No Known Activations