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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research objectives and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oms
    -0.16
    ansi
    -0.15
    .ManyToMany
    -0.15
    elda
    -0.15
    azz
    -0.15
    ầu
    -0.14
    iju
    -0.14
    evin
    -0.14
    pai
    -0.14
    ledi
    -0.14
    POSITIVE LOGITS
    aras
    0.19
    ingleton
    0.15
     Cros
    0.15
    uft
    0.15
    UPER
    0.15
    okers
    0.14
     hug
    0.14
    uario
    0.14
     nal
    0.14
    hend
    0.14
    Act Density 0.047%

    No Known Activations