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

    Neuronpedia

    INDEX
    Explanations

    references to financial concepts and journalistic credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndl
    -0.15
    typings
    -0.14
    eldo
    -0.14
    olver
    -0.14
    ongs
    -0.14
    Å¡k
    -0.14
    aiser
    -0.13
    bung
    -0.13
     beginning
    -0.13
    nds
    -0.13
    POSITIVE LOGITS
    Decoder
    0.24
     Monitor
    0.24
    Monitor
    0.22
     Decoder
    0.19
     hor
    0.18
    USA
    0.18
     monitor
    0.17
    .cs
    0.17
    hower
    0.17
    onitor
    0.16
    Act Density 0.003%

    No Known Activations