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

    Neuronpedia

    INDEX
    Explanations

    references to personal background and early life details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Benton
    -0.17
     beneficiation
    -0.16
     Benef
    -0.14
    efon
    -0.14
    egis
    -0.14
     è³
    -0.14
    Bounding
    -0.14
    BASH
    -0.14
     Buf
    -0.14
    ughs
    -0.14
    POSITIVE LOGITS
     born
    0.78
     birth
    0.66
     Born
    0.64
    -born
    0.61
    çĶŁ
    0.61
    Born
    0.60
    born
    0.59
     Birth
    0.52
    birth
    0.51
     births
    0.47
    Act Density 0.038%

    No Known Activations