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

    Neuronpedia

    INDEX
    Explanations

    references to methodologies and methods used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teen
    -0.17
    er
    -0.17
    itor
    -0.15
    ceptor
    -0.15
    ograd
    -0.15
    pars
    -0.15
    endor
    -0.15
    аÑĢÑĮ
    -0.15
    pig
    -0.15
    ninger
    -0.14
    POSITIVE LOGITS
    ical
    0.26
    ically
    0.25
    ologies
    0.24
    ological
    0.23
    icals
    0.19
    ologically
    0.18
    soever
    0.17
    ICAL
    0.17
    .Xaml
    0.16
    ology
    0.16
    Act Density 0.039%

    No Known Activations