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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the act of describing something

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of describing or explaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.78
    assi
    -0.78
    umo
    -0.72
    alos
    -0.71
    aghetti
    -0.71
    nown
    -0.69
    iasm
    -0.68
    ublic
    -0.68
    claimed
    -0.66
     Sabha
    -0.63
    POSITIVE LOGITS
     descriptions
    0.90
    urated
    0.76
    ript
    0.74
    urally
    0.73
    ĸļ
    0.72
     describ
    0.71
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    REDACTED
    0.70
     describing
    0.69
    enance
    0.69
    Act Density 0.028%

    No Known Activations