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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or disbelief

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -0.78
    
    -0.76
    Ārējās
    -0.69
     resourceCulture
    -0.65
     itſelf
    -0.65
     Stande
    -0.65
     Nonetheless
    -0.65
     uovo
    -0.65
     Diſ
    -0.64
     Pourtant
    -0.64
    POSITIVE LOGITS
     caisse
    0.59
    pexpr
    0.59
    bledon
    0.54
    /-/
    0.54
    esthes
    0.53
     Cake
    0.52
    olol
    0.51
     Dai
    0.50
    cieli
    0.49
    atmosfera
    0.49
    Act Density 0.011%

    No Known Activations