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

    Neuronpedia

    INDEX
    Explanations

    references to meta-concepts and self-referential commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udas
    -0.18
    asso
    -0.17
    achsen
    -0.15
     safety
    -0.14
     weight
    -0.14
    assic
    -0.14
     protection
    -0.14
     moll
    -0.14
    CO
    -0.14
     Brad
    -0.14
    POSITIVE LOGITS
    ngo
    0.17
    geries
    0.16
    Spatial
    0.15
    emple
    0.15
    afil
    0.15
     Gim
    0.14
    oure
    0.14
     ðŁĺī↵↵
    0.14
    ervo
    0.14
    765
    0.14
    Act Density 0.495%

    No Known Activations