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

    Neuronpedia

    INDEX
    Explanations

    phrases that mention both sides or multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention the concept of "both," particularly in contexts involving dualities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nob
    -0.74
    naire
    -0.72
     nowhere
    -0.72
    ifax
    -0.70
    uably
    -0.69
    \\\\\\\\
    -0.68
    lie
    -0.67
    ugu
    -0.66
    din
    -0.65
    lo
    -0.65
    POSITIVE LOGITS
     sexes
    1.60
     sides
    1.42
     halves
    1.34
     genders
    1.28
     parties
    0.94
     Houses
    0.92
     coasts
    0.90
     extremes
    0.90
     ends
    0.87
     directions
    0.86
    Act Density 0.057%

    No Known Activations