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

    Neuronpedia

    INDEX
    Explanations

    negative or questioning phrases or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaar
    -0.16
    aci
    -0.16
    bon
    -0.15
    .scalablytyped
    -0.14
    ulton
    -0.14
    alth
    -0.14
    uno
    -0.14
     nek
    -0.14
    ĵn
    -0.14
    antom
    -0.13
    POSITIVE LOGITS
    UPI
    0.16
    uddy
    0.15
    θή
    0.14
    rab
    0.14
    IGO
    0.14
    angi
    0.14
     Freem
    0.14
     repro
    0.14
     wells
    0.13
    woff
    0.13
    Act Density 0.003%

    No Known Activations