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

    Neuronpedia

    INDEX
    Explanations

    terms related to ongoing projects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.87
    vae
    -0.85
    gel
    -0.81
    ãģĦ
    -0.77
    combe
    -0.74
    dos
    -0.73
    DOS
    -0.72
    mson
    -0.71
    alties
    -0.69
    tesque
    -0.69
    POSITIVE LOGITS
     Gutenberg
    1.05
     undertaken
    0.98
    ors
    0.95
    ions
    0.81
    smanship
    0.81
    JECT
    0.80
    iverse
    0.80
    ivity
    0.79
     projects
    0.77
    ional
    0.76
    Act Density 0.042%

    No Known Activations