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

    Neuronpedia

    INDEX
    Explanations

    phrases that quantify or describe approximate amounts or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -1.04
    Portale
    -0.92
    expandindo
    -0.87
    Vidite
    -0.80
     EconPapers
    -0.79
     betweenstory
    -0.69
     cref
    -0.69
    Jereo
    -0.65
     فريبيس
    -0.63
    Hauptartikel
    -0.63
    POSITIVE LOGITS
     halfway
    0.86
     midway
    0.82
     midpoint
    0.66
     equal
    0.64
     equidist
    0.61
     mid
    0.60
     metà
    0.57
     half
    0.56
     evenly
    0.55
     midt
    0.53
    Act Density 0.157%

    No Known Activations