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

    Neuronpedia

    INDEX
    Explanations

    the word "Bon" along with variations of it at varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    the brand name "Bon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ODE
    -0.68
    ELD
    -0.67
    dfx
    -0.66
    INAL
    -0.65
    REAM
    -0.61
    LER
    -0.60
     Ethics
    -0.59
     Editorial
    -0.58
     fluids
    -0.58
    AY
    -0.57
    POSITIVE LOGITS
    anza
    1.32
    uses
    1.09
    kers
    1.08
    obos
    1.04
    eless
    1.03
    nie
    1.03
    iton
    1.03
    anz
    1.01
    bon
    1.00
    gey
    0.99
    Act Density 0.022%

    No Known Activations