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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to comparisons and evaluations of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
    رشف
    -0.66
    iNdEx
    -0.65
    calaureate
    -0.63
    SharedDtor
    -0.61
    +:+
    -0.61
    WireFormatLite
    -0.61
    principalTable
    -0.58
     snippetHide
    -0.58
    Autoritní
    -0.58
    POSITIVE LOGITS
     bad
    1.93
    bad
    1.56
     horrible
    1.55
     terrible
    1.55
     unpleasant
    1.53
     undesirable
    1.48
     BAD
    1.47
    Bad
    1.46
     nasty
    1.46
     awful
    1.45
    Act Density 0.731%

    No Known Activations