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

    Neuronpedia

    INDEX
    Explanations

    co-authors and creators of various works or studies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authorship and collaboration in research or creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.74
     peninsula
    -0.69
     millisec
    -0.68
     wo
    -0.65
     gou
    -0.63
     sidew
    -0.61
     gearing
    -0.61
     dysph
    -0.61
     Pog
    -0.61
     piercing
    -0.61
    POSITIVE LOGITS
    Initialized
    0.95
    cil
    0.94
    ership
    0.85
    edly
    0.84
     Cosponsors
    0.83
    sure
    0.77
    perse
    0.76
    ãĤ¦ãĤ¹
    0.73
    arters
    0.73
    tenance
    0.73
    Act Density 0.055%

    No Known Activations