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

    Neuronpedia

    INDEX
    Explanations

    questions indicated by the notation 'Q' at the beginning of the sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ague
    -0.17
    uju
    -0.16
    arez
    -0.16
     BIN
    -0.15
    unday
    -0.15
    IFIC
    -0.15
    QUIRE
    -0.15
    lac
    -0.15
     ÑĥÑģÑĤ
    -0.15
    QWidget
    -0.15
    POSITIVE LOGITS
    &A
    0.23
    antas
    0.21
    ubit
    0.21
    ubits
    0.20
    ued
    0.19
    uds
    0.18
    EMU
    0.18
    oS
    0.18
    atars
    0.18
    rious
    0.18
    Act Density 0.022%

    No Known Activations