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

    Neuronpedia

    INDEX
    Explanations

    references to requirements or necessities of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.71
    é¾
    -0.70
     Bom
    -0.68
    ourning
    -0.66
     rook
    -0.62
    å°Ĩ
    -0.60
     rabbit
    -0.59
    ws
    -0.59
     Guilty
    -0.58
    wikipedia
    -0.57
    POSITIVE LOGITS
    cale
    0.90
    lessly
    0.86
    giving
    0.80
     dictate
    0.74
     fulfilled
    0.69
    igslist
    0.69
    afe
    0.68
     domestically
    0.68
     constrained
    0.66
    etting
    0.66
    Act Density 0.027%

    No Known Activations