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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food and cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.15
    conti
    -0.15
    rosso
    -0.14
    okay
    -0.14
    abi
    -0.14
    Argb
    -0.13
    chg
    -0.13
     shitty
    -0.13
    æĺŃ
    -0.13
    annya
    -0.13
    POSITIVE LOGITS
     goodness
    0.38
     action
    0.29
     greatness
    0.29
     treat
    0.29
     fun
    0.28
     treats
    0.28
     aw
    0.26
     glory
    0.26
     magic
    0.25
    action
    0.24
    Act Density 0.313%

    No Known Activations