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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lau
    -0.78
    OTS
    -0.67
     2020
    -0.62
    ĻĤ
    -0.61
     Defenders
    -0.61
    Tri
    -0.57
     RIS
    -0.57
    ©¶æ
    -0.57
    Pocket
    -0.56
    POS
    -0.56
    POSITIVE LOGITS
    etheless
    1.06
    erous
    0.89
    uyomi
    0.89
    shore
    0.86
    creen
    0.82
    ettings
    0.82
    hett
    0.77
    .}
    0.76
    fleet
    0.74
    cially
    0.72
    Act Density 0.015%

    No Known Activations