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

    Neuronpedia

    INDEX
    Explanations

    topics related to legal and regulatory issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —are
    -0.16
    åĪĨåĪ«
    -0.16
    ,is
    -0.15
    Are
    -0.15
     Are
    -0.15
    arel
    -0.13
     když
    -0.13
    .↵
    -0.13
     Were
    -0.13
     sont
    -0.13
    POSITIVE LOGITS
     like
    0.35
     such
    0.32
     aside
    0.25
     similar
    0.23
    such
    0.22
     seperti
    0.22
     SUCH
    0.20
     zoals
    0.19
    Like
    0.18
     LIKE
    0.18
    Act Density 0.180%

    No Known Activations