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

    Neuronpedia

    INDEX
    Explanations

    references to different entrances and access points in a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beyond
    -0.16
    hta
    -0.15
    ott
    -0.15
    iciones
    -0.15
     Pend
    -0.14
    uj
    -0.14
     Downtown
    -0.14
    grave
    -0.14
     downstream
    -0.14
    roe
    -0.13
    POSITIVE LOGITS
     via
    0.17
    entry
    0.17
    via
    0.17
     conven
    0.16
    ergus
    0.15
    Via
    0.15
    Entry
    0.15
     entry
    0.15
    .entry
    0.15
     accessed
    0.15
    Act Density 0.071%

    No Known Activations