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

    Neuronpedia

    INDEX
    Explanations

    instances of societal or political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plusplus
    -0.17
    ambiguous
    -0.15
    "description
    -0.15
    ãĤĽ
    -0.15
    åŃĺäºİ
    -0.14
    otton
    -0.14
    alendar
    -0.14
    ausible
    -0.13
    ipur
    -0.13
    ypo
    -0.13
    POSITIVE LOGITS
     shows
    0.36
     indicates
    0.34
     show
    0.33
     indicate
    0.33
     demonstrate
    0.32
     demonstrates
    0.32
     speaks
    0.32
     att
    0.30
     speak
    0.29
     testify
    0.28
    Act Density 0.614%

    No Known Activations