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

    Neuronpedia

    INDEX
    Explanations

    terms related to different segments or phases within a context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different parts or segments of content or phases in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aganda
    -0.62
    Bir
    -0.62
    iverse
    -0.60
    inav
    -0.59
    pload
    -0.58
    itiveness
    -0.56
    inis
    -0.56
    isen
    -0.56
     Places
    -0.55
    anders
    -0.55
    POSITIVE LOGITS
     of
    1.32
     thereof
    1.19
    OF
    0.89
     OF
    0.86
    of
    0.86
     Of
    0.84
    Of
    0.82
    imester
    0.65
    rant
    0.64
    erest
    0.63
    Act Density 0.250%

    No Known Activations