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

    Neuronpedia

    INDEX
    Explanations

    references to software repositories and related actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of repositories or related terms in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.79
    ilipp
    -0.78
    stad
    -0.76
    cffffcc
    -0.76
    NetMessage
    -0.74
    ternity
    -0.74
    scar
    -0.73
    speak
    -0.73
    akening
    -0.72
    pher
    -0.72
    POSITIVE LOGITS
     repository
    1.30
     repositories
    1.22
     repo
    1.00
     stash
    0.83
     drawer
    0.77
     scaff
    0.72
    ositories
    0.72
     workspace
    0.71
     server
    0.71
     database
    0.69
    Act Density 0.011%

    No Known Activations