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

    Neuronpedia

    INDEX
    Explanations

    URLs ending in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snowball
    -0.58
     differe
    -0.56
     inner
    -0.55
     advancing
    -0.55
     notch
    -0.54
     retali
    -0.54
     streng
    -0.54
     constituent
    -0.54
     governors
    -0.53
     entangled
    -0.53
    POSITIVE LOGITS
    /?
    1.96
    /#
    1.72
    /_
    1.66
    /,
    1.64
    /)
    1.61
    /
    1.54
    /.
    1.53
    /-
    1.41
     âĢº
    1.40
    /+
    1.37
    Act Density 0.052%

    No Known Activations