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

    Neuronpedia

    INDEX
    Explanations

    verbs related to specific actions or events, particularly involving investigation or personal experience

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    resizeMode
    -0.58
    SizeMode
    -0.57
    shadowColor
    -0.55
     palab
    -0.55
    elezo
    -0.54
    Semitism
    -0.52
     miras
    -0.52
     GlobalKey
    -0.52
     ▼
    -0.51
    xpress
    -0.51
    POSITIVE LOGITS
     apprehen
    1.50
     shenan
    1.49
     unspeak
    1.46
     intersper
    1.43
     reluct
    1.28
     maneu
    1.27
     disagre
    1.25
     impra
    1.24
     gaily
    1.22
     indescri
    1.19
    Act Density 0.551%

    No Known Activations