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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trak
    -0.98
    ngth
    -0.76
    ayer
    -0.76
    ulhu
    -0.76
    cheat
    -0.75
    mination
    -0.75
    ère
    -0.71
    ruary
    -0.71
    jl
    -0.68
    ertodd
    -0.68
    POSITIVE LOGITS
     demographics
    1.04
     circumstances
    0.99
     sands
    0.97
     perspectives
    0.96
     technologies
    0.95
     directions
    0.94
     tides
    0.93
     attitudes
    0.90
     perceptions
    0.89
     climates
    0.89
    Act Density 0.019%

    No Known Activations