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

    Neuronpedia

    INDEX
    Explanations

    words pertaining to food descriptions or types of cuisine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nya
    -0.34
    y
    -0.32
    li
    -0.32
    me
    -0.31
    pro
    -0.30
    mente
    -0.29
    ka
    -0.29
    so
    -0.28
    v
    -0.28
    ger
    -0.28
    POSITIVE LOGITS
    Ùĭ
    0.29
    ugh
    0.29
    'nın
    0.29
    frica
    0.29
    ’nın
    0.28
    oui
    0.25
    issance
    0.25
    ught
    0.25
    eus
    0.25
    ughty
    0.24
    Act Density 0.931%

    No Known Activations