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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to political or bilateral contexts where multiple entities are involved

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "both" to indicate consideration of two opposing sides or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lé
    -0.75
    ugu
    -0.74
    potion
    -0.73
    lo
    -0.71
    uez
    -0.70
    dq
    -0.69
    vez
    -0.68
    ¥
    -0.67
    renheit
    -0.67
    eln
    -0.66
    POSITIVE LOGITS
     sexes
    1.52
     genders
    1.28
     sides
    1.28
     halves
    1.27
     parties
    0.89
     ends
    0.84
     kinds
    0.84
     extremes
    0.83
    ocating
    0.83
     coasts
    0.80
    Act Density 0.048%

    No Known Activations