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

    Neuronpedia

    INDEX
    Explanations

    differences or distinctions between entities

    oai_token-act-pair · gpt-3.5-turbo

    the concept of differences or comparisons between various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.87
    di
    -0.76
    idth
    -0.75
    bed
    -0.74
    tsky
    -0.74
    daq
    -0.72
    ãĤ¡
    -0.72
    der
    -0.71
    bye
    -0.70
    IDE
    -0.70
    POSITIVE LOGITS
     sexes
    0.94
     genders
    0.94
     halves
    0.81
     them
    0.69
     Nanto
    0.69
     thirds
    0.68
     peoples
    0.68
     eras
    0.64
    iating
    0.63
     levels
    0.63
    Act Density 0.044%

    No Known Activations