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

    Neuronpedia

    INDEX
    Explanations

    the word "this" followed by further information or context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" indicating focus on specific events or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¹ãĥĪ
    -0.81
    ãĥ¼ãĥ³
    -0.80
    istries
    -0.75
    ãĥ©ãĥ³
    -0.75
    anamo
    -0.73
    isms
    -0.72
    adle
    -0.72
    ãĤ¬
    -0.72
    cks
    -0.71
    ortment
    -0.71
    POSITIVE LOGITS
     trope
    0.94
     particular
    0.90
     arrangement
    0.90
     happened
    0.84
     newfound
    0.83
     phenomenon
    0.83
     enigmatic
    0.82
     nifty
    0.81
     latest
    0.80
     guy
    0.80
    Act Density 0.139%

    No Known Activations