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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating demonstration or presentation of results and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orp
    -0.16
     padd
    -0.15
    ustr
    -0.15
    emme
    -0.14
    vara
    -0.14
    ilen
    -0.14
     paddle
    -0.14
    ä¾
    -0.13
    usa
    -0.13
    Hostname
    -0.13
    POSITIVE LOGITS
    ered
    0.19
    erver
    0.16
    ´
    0.15
    okedex
    0.15
    314
    0.14
    agers
    0.14
    erring
    0.14
    .gg
    0.14
    ermo
    0.13
    ager
    0.13
    Act Density 0.102%

    No Known Activations