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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and phrases that convey emphasis or exaggeration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autowired
    -0.52
     oczywiście
    -0.50
    Ensuite
    -0.50
    specifier
    -0.48
    kegaard
    -0.47
     cạnh
    -0.46
     presumably
    -0.45
     Traditionally
    -0.45
     traditionally
    -0.45
    Parti
    -0.45
    POSITIVE LOGITS
     literally
    0.92
     Literally
    0.87
    literally
    0.86
    Literally
    0.85
     literalmente
    0.84
     truly
    0.81
    truly
    0.80
     Truly
    0.80
    Truly
    0.77
    IVEREF
    0.76
    Act Density 0.089%

    No Known Activations