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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating specific numerical limits and classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illi
    -0.17
    rana
    -0.16
    ieber
    -0.15
    leo
    -0.15
    ras
    -0.15
    üy
    -0.15
     kv
    -0.14
    kv
    -0.14
    ulis
    -0.14
    venta
    -0.14
    POSITIVE LOGITS
    ģn
    0.16
    ORN
    0.14
     Rem
    0.14
     rem
    0.14
     ten
    0.14
    Rem
    0.13
     Buck
    0.13
    ë¡ľëĬĶ
    0.13
     Demp
    0.13
     ist
    0.13
    Act Density 0.047%

    No Known Activations