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

    Neuronpedia

    INDEX
    Explanations

    the word "This" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to specific situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¹ãĥĪ
    -0.96
    omo
    -0.84
    adle
    -0.76
    Ñĥ
    -0.74
    ãĥ©ãĥ³
    -0.71
    ãĤ½
    -0.70
    ãĥı
    -0.70
    ©¶æ¥µ
    -0.69
    Ĭ±
    -0.69
    Ń·
    -0.69
    POSITIVE LOGITS
     week
    0.98
     guy
    0.97
     year
    0.89
     morning
    0.86
     incarnation
    0.85
     weekend
    0.81
     particular
    0.80
     latest
    0.79
     iteration
    0.79
     isn
    0.78
    Act Density 0.206%

    No Known Activations