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

    Neuronpedia

    INDEX
    Explanations

    references to weight loss strategies and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤÑĥ
    -0.15
    aus
    -0.15
    hero
    -0.14
    orum
    -0.13
    vore
    -0.13
     thermometer
    -0.13
     Stake
    -0.13
    onth
    -0.13
     spur
    -0.13
     bis
    -0.13
    POSITIVE LOGITS
    -scrollbar
    0.15
    untu
    0.15
     Shack
    0.15
     Hak
    0.14
    elic
    0.14
    adius
    0.14
    elligence
    0.14
    eum
    0.14
    ervas
    0.14
    ucas
    0.14
    Act Density 0.004%

    No Known Activations