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

    Neuronpedia

    INDEX
    Explanations

    sentences with a direct quotation structure

    oai_token-act-pair · gpt-3.5-turbo

    indications of positive or affirmative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     range
    -0.70
     semblance
    -0.66
     raft
    -0.66
     classification
    -0.65
     FAR
    -0.64
     fragmentation
    -0.64
     shelf
    -0.64
     round
    -0.63
     shroud
    -0.63
     Round
    -0.63
    POSITIVE LOGITS
    sure
    1.03
    ł
    0.97
    ¹
    0.90
    said
    0.89
    ª
    0.88
    there
    0.88
    especially
    0.88
    then
    0.86
    perhaps
    0.86
    must
    0.84
    Act Density 0.071%

    No Known Activations