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

    Neuronpedia

    INDEX
    Explanations

    elements related to blog posts and author contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asher
    -0.15
    à¹ĩà¸Ķ
    -0.15
     Weber
    -0.15
    chein
    -0.14
     Tos
    -0.14
    etto
    -0.14
    (label
    -0.14
    åħIJ
    -0.14
    zc
    -0.14
    label
    -0.14
    POSITIVE LOGITS
    Tags
    0.80
     Tags
    0.78
     tags
    0.68
    _tags
    0.61
    -tags
    0.59
    .tags
    0.55
    tags
    0.54
    .Tags
    0.51
    (tags
    0.48
    _TAGS
    0.47
    Act Density 0.053%

    No Known Activations