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

    Neuronpedia

    INDEX
    Explanations

    words related to issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    the significance of various topics indicated by the word "matters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARP
    -0.89
    ãĥ³ãĤ¸
    -0.81
    ARK
    -0.76
     ceiling
    -0.76
    ©¶æ
    -0.67
    Tur
    -0.66
    urses
    -0.66
    asio
    -0.65
    asters
    -0.63
    thia
    -0.63
    POSITIVE LOGITS
     matters
    1.00
    cale
    0.94
    matter
    0.93
    enance
    0.89
    pace
    0.88
    manship
    0.86
     Matters
    0.85
    rament
    0.83
    icult
    0.81
    hip
    0.76
    Act Density 0.013%

    No Known Activations