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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements or comparisons, particularly involving the word "scales."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurement and scaling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    present
    -0.76
    vent
    -0.74
    draw
    -0.73
    riad
    -0.72
    conn
    -0.69
     Gore
    -0.68
    VP
    -0.68
    algia
    -0.66
     McGu
    -0.64
    vous
    -0.64
    POSITIVE LOGITS
     scales
    1.45
    heet
    0.90
     scale
    0.90
     Scale
    0.84
    itized
    0.82
     shards
    0.82
    iless
    0.79
     peanuts
    0.76
     straps
    0.76
    acebook
    0.74
    Act Density 0.004%

    No Known Activations