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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts between two ideas

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating duality or contrasting qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugu
    -0.83
    lé
    -0.70
    uez
    -0.70
    renheit
    -0.70
    ilit
    -0.67
     Kard
    -0.66
    dq
    -0.65
    acion
    -0.64
    lus
    -0.63
    lic
    -0.63
    POSITIVE LOGITS
     sexes
    1.50
     sides
    1.31
     halves
    1.26
     genders
    1.23
     thirds
    0.83
    ocating
    0.81
     ends
    0.78
     senses
    0.75
     parties
    0.74
     kinds
    0.73
    Act Density 0.052%

    No Known Activations