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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and references commonly used in academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [:,:,
    -0.58
    ropra
    -0.54
     Zelanda
    -0.52
     virš
    -0.52
     выстав
    -0.51
    ouncy
    -0.51
    mediately
    -0.50
    corrhi
    -0.49
    RIST
    -0.49
    StringCopy
    -0.48
    POSITIVE LOGITS
    ✨:
    0.70
    utnik
    0.69
    Билгалдахарш
    0.64
    PROLOG
    0.64
     PhpStorm
    0.64
     Ilya
    0.63
     peculiarities
    0.63
    yandex
    0.61
     semej
    0.61
     imago
    0.60
    Act Density 0.478%

    No Known Activations