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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to separation or division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to separation and reparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demise
    -0.73
     success
    -0.72
     permitting
    -0.69
     column
    -0.68
     Lol
    -0.68
     Elys
    -0.67
     bullish
    -0.65
    cloud
    -0.65
     millennial
    -0.64
     Plum
    -0.64
    POSITIVE LOGITS
    arate
    4.01
    aration
    3.18
    arations
    2.63
    arat
    1.39
    aque
    1.22
    atana
    1.22
    aques
    1.21
    arant
    1.15
    ar
    1.13
    aram
    1.09
    Act Density 0.035%

    No Known Activations