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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or technical details

    oai_token-act-pair · gpt-3.5-turbo

    references to electrical appliances and their safety instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.56
     Helic
    -0.55
    fol
    -0.54
    NetMessage
    -0.52
    gew
    -0.52
     Faul
    -0.50
    bris
    -0.50
     Brist
    -0.49
     Prem
    -0.49
    grab
    -0.49
    POSITIVE LOGITS
    endif
    0.64
    TextColor
    0.59
    orgetown
    0.57
    hover
    0.55
    miah
    0.54
    celona
    0.54
    ovi
    0.53
     Logged
    0.51
    pton
    0.51
    oser
    0.51
    Act Density 0.866%

    No Known Activations