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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inals
    -0.17
    uffman
    -0.17
    imbus
    -0.16
     oslo
    -0.15
    ipi
    -0.14
    tered
    -0.14
    rov
    -0.14
    fter
    -0.14
    duino
    -0.14
    isors
    -0.14
    POSITIVE LOGITS
    627
    0.21
    620
    0.16
    626
    0.15
    308
    0.14
    cci
    0.14
    chl
    0.14
     monoc
    0.14
    icie
    0.14
    .RightToLeft
    0.14
    572
    0.14
    Act Density 0.189%

    No Known Activations