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

    Neuronpedia

    INDEX
    Explanations

    utterances that involve direct address or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grily
    -0.15
    ults
    -0.15
    @qq
    -0.14
     cấp
    -0.14
    urse
    -0.14
    vos
    -0.14
    usz
    -0.14
    nist
    -0.14
    usercontent
    -0.14
    osi
    -0.13
    POSITIVE LOGITS
    uu
    0.19
     said
    0.17
     two
    0.16
     sir
    0.16
     should
    0.16
     sure
    0.16
     know
    0.16
    re
    0.15
     header
    0.15
     certainly
    0.15
    Act Density 0.125%

    No Known Activations