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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'Q' followed by non-zero activations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ague
    -0.19
    uju
    -0.17
    arez
    -0.16
     ÑĥÑģÑĤ
    -0.15
    unday
    -0.15
    lac
    -0.15
     BIN
    -0.15
    ACEMENT
    -0.14
    IFIC
    -0.14
    èįĴ
    -0.14
    POSITIVE LOGITS
    &A
    0.21
    ued
    0.21
    antas
    0.20
    ubit
    0.20
    oS
    0.20
    wick
    0.19
    ubits
    0.19
    uds
    0.18
    ues
    0.18
    outes
    0.18
    Act Density 0.022%

    No Known Activations