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

    Neuronpedia

    INDEX
    Explanations

    words related to assistance, collaboration, or support

    oai_token-act-pair · gpt-3.5-turbo

    words related to assistance, support, or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urai
    -0.66
    owe
    -0.59
     Origin
    -0.58
    oro
    -0.58
     Kinnikuman
    -0.58
    essage
    -0.55
    hur
    -0.54
    ç«
    -0.53
     Doctrine
    -0.53
     Tribunal
    -0.53
    POSITIVE LOGITS
     by
    1.40
    by
    1.26
    By
    1.08
     BY
    1.05
     By
    0.99
    Ń·
    0.97
    bys
    0.96
     aback
    0.86
    BY
    0.83
    ĸļ
    0.74
    Act Density 0.329%

    No Known Activations