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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or suggestions regarding actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.95
     autorytatywna
    -0.82
    typeorm
    -0.81
    хьтан
    -0.75
    CloseOperation
    -0.74
    awtextra
    -0.73
    readystatechange
    -0.71
     sqlSession
    -0.71
    conio
    -0.70
    AsUp
    -0.69
    POSITIVE LOGITS
     the
    0.67
     these
    0.63
     such
    0.62
     hés
    0.57
     nélk
    0.54
     between
    0.53
     a
    0.51
     this
    0.50
     związ
    0.50
    iedad
    0.49
    Act Density 0.350%

    No Known Activations