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

    Neuronpedia

    INDEX
    Explanations

    words related to conflicts and disputes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conf" which likely indicates it is looking for discussions on confusion or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.93
    hyde
    -0.81
    ©¶æ
    -0.78
    DAY
    -0.77
    schild
    -0.71
    manship
    -0.69
    ï¸ı
    -0.68
    etheless
    -0.68
    BALL
    -0.66
    beit
    -0.66
    POSITIVE LOGITS
    luence
    1.10
    ederation
    1.10
    essional
    1.05
    usions
    1.03
    eder
    1.02
    licted
    0.94
    eree
    0.91
    usional
    0.89
    etti
    0.86
    erences
    0.82
    Act Density 0.004%

    No Known Activations