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

    Neuronpedia

    INDEX
    Explanations

    words related to freedom, flexibility, caution, thought, pride, attention, enthusiasm, effort, weight, passion, and disagreement in a context that suggests decision-making or judgment

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to power, discretion, and variability in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Avenger
    -0.68
     quint
    -0.64
     arr
    -0.60
     lookout
    -0.60
    nder
    -0.59
    ynchron
    -0.58
     fold
    -0.55
     tractor
    -0.55
     pist
    -0.55
     Schl
    -0.55
    POSITIVE LOGITS
    smanship
    0.77
     whatsoever
    0.74
     (>
    0.73
     regarding
    0.72
    actionDate
    0.69
     considering
    0.67
    ãĤ¶
    0.67
    é¾įå¥ij士
    0.66
    ãĤ¬
    0.66
    tests
    0.64
    Act Density 0.284%

    No Known Activations