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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a foundational or fundamental aspect of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "base" followed by a numeric value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.79
    NESS
    -0.77
    oso
    -0.76
    apes
    -0.73
    icer
    -0.70
    inness
    -0.67
    istor
    -0.67
     Rebell
    -0.66
    icut
    -0.66
    ROR
    -0.66
    POSITIVE LOGITS
    camp
    1.12
    plate
    0.97
    plates
    0.96
    ball
    0.85
     erosion
    0.82
    rame
    0.77
    BALL
    0.76
    plan
    0.76
    bridge
    0.72
    band
    0.72
    Act Density 0.015%

    No Known Activations