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

    Neuronpedia

    INDEX
    Explanations

    words related to formal agreements or treaties

    oai_token-act-pair · gpt-3.5-turbo

    references to agreements or accords, particularly in a political or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GER
    -0.83
    ################
    -0.68
    lycer
    -0.65
    AAF
    -0.62
    DER
    -0.61
    APD
    -0.61
     Ku
    -0.61
     FSA
    -0.60
     inhib
    -0.60
    GGGGGGGG
    -0.60
    POSITIVE LOGITS
    ion
    1.02
    ords
    1.00
    ioned
    0.96
    ions
    0.90
    forth
    0.89
    ious
    0.84
    ered
    0.84
    ivalent
    0.82
    ian
    0.81
    romeda
    0.79
    Act Density 0.052%

    No Known Activations