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

    Neuronpedia

    INDEX
    Explanations

    URL links, especially those pointing to specific resources within a technical platform

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.91
    interstitial
    -0.83
     conclud
    -0.79
    avorite
    -0.76
    uggest
    -0.76
    eatures
    -0.71
     behavi
    -0.68
    sylv
    -0.66
    Sov
    -0.65
    entimes
    -0.65
    POSITIVE LOGITS
     etc
    1.10
     et
    0.74
    ...)
    0.72
    ioch
    0.71
    )"
    0.69
     preferably
    0.68
     sizeof
    0.68
     whence
    0.67
     partName
    0.66
     uint
    0.65
    Act Density 0.234%

    No Known Activations