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

    Neuronpedia

    INDEX
    Explanations

    references to professional work, contributions, and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     worked
    -0.15
     Gem
    -0.15
     should
    -0.14
    abez
    -0.14
    coder
    -0.13
     Works
    -0.13
    should
    -0.13
    aret
    -0.13
    Needs
    -0.13
    Gem
    -0.13
    POSITIVE LOGITS
     ranges
    0.31
     crosses
    0.25
    ranges
    0.24
     str
    0.24
     ranged
    0.22
     spans
    0.21
     bridges
    0.20
     covers
    0.19
     range
    0.19
     touches
    0.19
    Act Density 0.099%

    No Known Activations