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

    Neuronpedia

    INDEX
    Explanations

    requests to avoid editing or modifying content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.75
     ſeveral
    -0.68
    enapa
    -0.66
    MMV
    -0.64
     uſed
    -0.64
     doubtnut
    -0.63
     pleaſure
    -0.63
    setVerticalGroup
    -0.62
    writeFieldEnd
    -0.61
    ENEFITS
    -0.61
    POSITIVE LOGITS
     or
    0.60
     незавершена
    0.59
     too
    0.56
    too
    0.55
    .
    0.52
    this
    0.49
     nor
    0.48
    强的
    0.45
    ,
    0.45
    ^
    0.44
    Act Density 0.400%

    No Known Activations