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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate breadth or variety of subject matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viated
    -0.58
    ttl
    -0.54
    olescence
    -0.51
    Clu
    -0.49
     Bump
    -0.48
     التر
    -0.47
     bump
    -0.47
    clu
    -0.47
     meneg
    -0.46
     bumping
    -0.46
    POSITIVE LOGITS
     range
    1.03
    Range
    1.00
     spectrum
    0.95
     RANGE
    0.92
    spectrum
    0.86
     Range
    0.85
    Spectrum
    0.85
     Spectrum
    0.84
    RANGE
    0.78
    Ranges
    0.77
    Act Density 0.113%

    No Known Activations