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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coding commands and instructions

    oai_token-act-pair · gpt-3.5-turbo

    fragments of code or programming-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machina
    -0.77
    )].
    -0.71
     Archdemon
    -0.71
     trope
    -0.70
    ylum
    -0.66
     Inquis
    -0.66
     Canter
    -0.65
    externalActionCode
    -0.63
     Syndrome
    -0.62
     beams
    -0.61
    POSITIVE LOGITS
    password
    0.84
     ~/.
    0.82
    USER
    0.81
    mb
    0.81
     sudo
    0.79
    Password
    0.78
     $(
    0.78
    Debug
    0.78
    ctr
    0.78
    raw
    0.77
    Act Density 0.154%

    No Known Activations