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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or boundaries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Waldo
    -0.63
     heirs
    -0.59
    ArrowToggle
    -0.58
     uſed
    -0.58
    RegressionTest
    -0.57
     houſe
    -0.56
    himu
    -0.56
     ſeveral
    -0.55
     heir
    -0.54
     purpoſe
    -0.54
    POSITIVE LOGITS
    MigrationBuilder
    0.70
    SourceChecksum
    0.64
    awtextra
    0.64
     تعدى
    0.62
     خارجية
    0.61
     !!}
    0.58
    ])):
    0.55
    writeFieldEnd
    0.53
    ]:
    0.52
    */].
    0.51
    Act Density 0.238%

    No Known Activations