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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "about" followed by other content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hearing or learning about various topics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.87
    terness
    -0.71
    ocene
    -0.68
    wig
    -0.66
    hesis
    -0.65
    hai
    -0.65
    ulla
    -0.64
    assi
    -0.63
    alon
    -0.62
    estyles
    -0.62
    POSITIVE LOGITS
     them
    0.68
     how
    0.67
    PsyNetMessage
    0.67
     EB
    0.60
     halfway
    0.60
     Bund
    0.60
     him
    0.60
     unpublished
    0.59
     bund
    0.59
     vulnerabilities
    0.58
    Act Density 0.088%

    No Known Activations