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

    Neuronpedia

    INDEX
    Explanations

    requests or commands for someone to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of requesting or asking actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.73
    NetMessage
    -0.71
    ggle
    -0.67
    urches
    -0.67
    ctory
    -0.66
     shrug
    -0.65
    itiveness
    -0.64
     instinctively
    -0.64
    +)
    -0.63
     seams
    -0.63
    POSITIVE LOGITS
     someday
    0.94
     ASAP
    0.81
     tomorrow
    0.69
     anonymously
    0.66
     next
    0.63
     Ghostbusters
    0.62
     «
    0.62
    ãĥĩ
    0.62
     drawings
    0.61
     Cipher
    0.61
    Act Density 0.965%

    No Known Activations