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

    Neuronpedia

    INDEX
    Explanations

    titles and names associated with literary works and artistic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Performs
    -0.18
     Appears
    -0.17
     disappears
    -0.17
     Determines
    -0.16
     becomes
    -0.16
    Produces
    -0.16
     ÙĨدارد
    -0.16
     ÑģÑĤановиÑĤÑģÑı
    -0.15
     DOES
    -0.15
     Indicates
    -0.15
    POSITIVE LOGITS
     encaps
    0.26
    explo
    0.24
     centers
    0.23
     recre
    0.23
     features
    0.23
     traces
    0.23
     chron
    0.23
     plung
    0.22
     exempl
    0.22
     probes
    0.22
    Act Density 0.374%

    No Known Activations