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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaranya
    -0.55
    TagMode
    -0.52
    انتهای
    -0.51
    them
    -0.49
     sorter
    -0.48
    ikkert
    -0.47
    herself
    -0.47
     henne
    -0.47
    aternion
    -0.44
     Alva
    -0.43
    POSITIVE LOGITS
     there
    1.16
     they
    1.08
     it
    0.94
     we
    0.94
     nobody
    0.90
     evidenced
    0.82
    there
    0.82
     although
    0.79
     many
    0.77
     none
    0.77
    Act Density 0.168%

    No Known Activations