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

    Neuronpedia

    INDEX
    Explanations

    special characters or unique symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighter
    -0.16
     VH
    -0.15
    orda
    -0.15
    alom
    -0.14
    illow
    -0.14
    eln
    -0.14
    ripper
    -0.14
     LH
    -0.14
     ‘
    -0.14
     Hamburg
    -0.13
    POSITIVE LOGITS
     Indigenous
    0.35
     Stanley
    0.30
     Indians
    0.28
     Native
    0.26
    Stan
    0.26
     colon
    0.25
     colonial
    0.25
     Colonial
    0.25
     Colon
    0.24
     Indian
    0.24
    Act Density 0.003%

    No Known Activations