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

    Neuronpedia

    INDEX
    Explanations

    elements of conversation that indicate relationships and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éº
    -0.16
    OF
    -0.15
    ampus
    -0.14
    alse
    -0.14
    ör
    -0.14
    agoon
    -0.13
    EDIUM
    -0.13
    URING
    -0.13
    çon
    -0.13
     smart
    -0.13
    POSITIVE LOGITS
    ingroup
    0.16
    rowable
    0.15
    éĢł
    0.15
    ulumi
    0.15
     Compilation
    0.14
     cont
    0.14
    nob
    0.14
    æľĢè¿ij
    0.14
    лади
    0.14
    çļ
    0.14
    Act Density 0.525%

    No Known Activations