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

    Neuronpedia

    INDEX
    Explanations

    terms related to attention, recognition, and awareness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attention and coverage of specific topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.80
    tta
    -0.72
    ©¶æ
    -0.71
     Alone
    -0.71
    artifacts
    -0.69
    vable
    -0.68
    puter
    -0.68
    hid
    -0.67
    Plan
    -0.66
    ramid
    -0.66
    POSITIVE LOGITS
     attention
    1.59
     notoriety
    1.42
     acclaim
    1.41
     publicity
    1.33
     applause
    1.32
     traction
    1.25
     ire
    1.24
     accol
    1.22
     praise
    1.19
     scorn
    1.15
    Act Density 0.183%

    No Known Activations