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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes of decision-making and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.15
    áºŃu
    -0.14
    acz
    -0.14
    okus
    -0.14
    OLS
    -0.14
    engl
    -0.13
    ollow
    -0.13
     برد
    -0.13
    etten
    -0.13
    ugu
    -0.13
    POSITIVE LOGITS
     iron
    0.36
    iron
    0.32
     Iron
    0.30
     sorted
    0.30
    Iron
    0.27
     sorting
    0.27
    IRON
    0.24
     Sorting
    0.24
     hashed
    0.24
     hammered
    0.24
    Act Density 0.136%

    No Known Activations