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

    Neuronpedia

    INDEX
    Explanations

    words related to machines, tools, and technical equipment

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms associated with scientific concepts or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.67
     Day
    -0.66
     Reviews
    -0.64
    WER
    -0.62
    WD
    -0.61
    ornings
    -0.61
    Weather
    -0.61
    Ħ
    -0.61
     Own
    -0.60
    ¶æ
    -0.60
    POSITIVE LOGITS
    iest
    1.13
    liest
    0.98
     fallacy
    0.89
    omial
    0.84
    osphere
    0.80
     hypothesis
    0.79
     portion
    0.77
    iness
    0.74
     phase
    0.73
     brigade
    0.72
    Act Density 0.312%

    No Known Activations