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

    Neuronpedia

    INDEX
    Explanations

    words related to international events or relations

    oai_token-act-pair · gpt-3.5-turbo

    frequent conjunctions and prepositions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rored
    -0.67
    ÑĮ
    -0.59
    tymology
    -0.59
    Å«
    -0.57
    algia
    -0.57
    onents
    -0.56
    ĨĴ
    -0.56
    ocal
    -0.55
    iture
    -0.54
    ĩ
    -0.54
    POSITIVE LOGITS
     thereby
    1.03
     thence
    0.78
     respectively
    0.74
     lest
    0.72
     THEN
    0.71
     preferably
    0.68
     then
    0.68
    instead
    0.66
     thereafter
    0.66
     eliminates
    0.66
    Act Density 0.785%

    No Known Activations