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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eil
    -0.14
    azz
    -0.14
    ÃŃo
    -0.14
    isz
    -0.14
     crow
    -0.14
    çĪ¾
    -0.14
    ourcing
    -0.13
     Wick
    -0.13
    ÐĴÑĸн
    -0.13
     shops
    -0.13
    POSITIVE LOGITS
    anje
    0.16
    itizer
    0.15
    anth
    0.15
    bine
    0.14
     [|
    0.14
    sweet
    0.14
    uplic
    0.14
    BIND
    0.14
    ÙĨاÙĨ
    0.14
     бла
    0.14
    Act Density 0.309%

    No Known Activations