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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and references to food-related items and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vintage
    -0.15
    undred
    -0.15
    645
    -0.14
     navr
    -0.14
    emer
    -0.14
    leted
    -0.14
    ours
    -0.14
    lus
    -0.14
    uster
    -0.13
    phere
    -0.13
    POSITIVE LOGITS
    ÑĤаб
    0.15
     Rays
    0.15
    agus
    0.15
    -shaped
    0.14
    Ĥ¹
    0.14
     Morav
    0.13
    Hallo
    0.13
    iko
    0.13
    eyed
    0.13
    師
    0.13
    Act Density 0.563%

    No Known Activations