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

    Neuronpedia

    INDEX
    Explanations

    significant events or milestones

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or milestones related to first occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pots
    -0.62
    eele
    -0.60
    oros
    -0.58
    xual
    -0.58
    ngth
    -0.58
    nets
    -0.57
    ulty
    -0.56
    ²¾
    -0.55
     Provided
    -0.55
    姫
    -0.55
    POSITIVE LOGITS
     first
    1.36
     sixth
    1.34
     fourth
    1.33
     fifth
    1.33
     seventh
    1.31
     eighth
    1.31
     third
    1.28
     ninth
    1.28
     second
    1.20
    first
    1.20
    Act Density 0.233%

    No Known Activations