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

    Neuronpedia

    INDEX
    Explanations

    conversational cues and elements of dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.18
    Ä°s
    -0.17
    sono
    -0.16
    ILON
    -0.15
    ÏĥÏĦα
    -0.15
    JsonValue
    -0.15
     важ
    -0.15
    important
    -0.14
    angu
    -0.14
     wiÄĻc
    -0.14
    POSITIVE LOGITS
     then
    0.21
     THEN
    0.19
    Then
    0.17
    .Or
    0.16
     or
    0.16
    è¿Ļæł·
    0.16
     Then
    0.16
     would
    0.16
     Or
    0.16
    then
    0.16
    Act Density 0.141%

    No Known Activations