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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of discovering or revealing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.17
    ména
    -0.15
    gio
    -0.15
    аннÑĸ
    -0.14
    umblr
    -0.14
    zel
    -0.14
    ÑĢаб
    -0.14
    atra
    -0.14
    yny
    -0.14
    ccione
    -0.14
    POSITIVE LOGITS
    ierz
    0.16
    awah
    0.14
    816
    0.14
    .preferences
    0.14
    (
    0.14
     Gree
    0.13
    Formatting
    0.13
    avigate
    0.13
    ocard
    0.13
    ettings
    0.13
    Act Density 0.006%

    No Known Activations