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

    Neuronpedia

    INDEX
    Explanations

    mixtures or blends of ingredients in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    references to mixtures and their preparation in cooking contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.90
    voice
    -0.77
    ®
    -0.76
    ORT
    -0.74
    ORD
    -0.73
    orth
    -0.70
    å¸
    -0.69
    sych
    -0.68
    ¯
    -0.67
    £
    -0.66
    POSITIVE LOGITS
     mixture
    0.98
     conco
    0.95
     containing
    0.90
     ingested
    0.89
     powd
    0.84
     soluble
    0.83
     contamin
    0.82
     blends
    0.81
    roleum
    0.81
     contents
    0.80
    Act Density 0.071%

    No Known Activations