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

    Neuronpedia

    INDEX
    Explanations

    topics related to global and national news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zos
    -0.17
    erdale
    -0.16
    .Dom
    -0.15
    iaux
    -0.15
    gı
    -0.14
    abela
    -0.14
    uhan
    -0.14
    kovi
    -0.14
    verity
    -0.14
     Enumeration
    -0.14
    POSITIVE LOGITS
    naments
    0.16
    anch
    0.16
     Ble
    0.16
    ertools
    0.16
    ules
    0.15
     Sa
    0.15
    anta
    0.14
    egin
    0.14
    affle
    0.14
    riv
    0.14
    Act Density 0.009%

    No Known Activations