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

    Neuronpedia

    INDEX
    Explanations

    terms related to tools or equipment

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that refer to various objects or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KNOWN
    -0.65
     citiz
    -0.65
     practition
    -0.63
     carbohyd
    -0.63
     newsp
    -0.62
    Qual
    -0.58
    GoldMagikarp
    -0.58
    Mech
    -0.58
    ¾
    -0.58
    Loop
    -0.58
    POSITIVE LOGITS
    mith
    1.14
    cale
    1.13
    hare
    1.09
    poons
    1.08
    creen
    1.07
    hots
    1.06
    ynthesis
    1.04
    heet
    1.01
    ktop
    1.00
    etting
    1.00
    Act Density 0.421%

    No Known Activations