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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to a product

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.60
     vainly
    -1.19
     pamph
    -1.16
     philosophic
    -1.12
     reconno
    -1.12
     endeavouring
    -1.10
     poetical
    -1.09
     gaily
    -1.08
     apprehen
    -1.06
     murmuring
    -1.06
    POSITIVE LOGITS
     ananas
    1.65
     moza
    1.63
     elek
    1.58
     maniere
    1.56
     utop
    1.53
     lapto
    1.52
     marte
    1.51
     karton
    1.51
     torba
    1.50
     lampa
    1.49
    Act Density 0.236%

    No Known Activations