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

    Neuronpedia

    INDEX
    Explanations

    references to undisclosed or unspecified information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to undisclosed or unspecified amounts and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingo
    -0.84
    ynthesis
    -0.82
    hedral
    -0.79
    aldi
    -0.78
    mong
    -0.77
    acco
    -0.77
    anooga
    -0.76
    =-=-=-=-=-=-=-=-
    -0.73
    chev
    -0.72
    abies
    -0.71
    POSITIVE LOGITS
     unspecified
    0.86
     undisclosed
    0.84
     TBA
    0.74
    =]
    0.73
    theless
    0.71
     amounts
    0.69
    ãĤ¯
    0.69
     NX
    0.69
    ],[
    0.69
    itarian
    0.66
    Act Density 0.012%

    No Known Activations