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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with 'for instance' or 'however'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "instance" or phrases indicating examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nightmare
    -0.64
     canopy
    -0.62
     coverage
    -0.61
     windows
    -0.60
     laure
    -0.59
     exposition
    -0.58
     antioxid
    -0.57
     seams
    -0.56
     sshd
    -0.56
     Columb
    -0.55
    POSITIVE LOGITS
    inki
    0.75
    rongh
    0.72
    adle
    0.70
    utenberg
    0.69
    imaru
    0.67
     namely
    0.67
    uld
    0.67
    paio
    0.66
    éĢ
    0.66
    cipl
    0.66
    Act Density 0.113%

    No Known Activations