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

    Neuronpedia

    INDEX
    Explanations

    descriptions involving events or situations happening over time

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant changes or contrasts in experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.82
    olor
    -0.75
    ibliography
    -0.69
    sequently
    -0.69
     thereafter
    -0.64
    arine
    -0.63
     later
    -0.61
    then
    -0.61
     periodic
    -0.61
    ournals
    -0.60
    POSITIVE LOGITS
     instead
    0.79
    instead
    0.78
     opted
    0.75
    quickShipAvailable
    0.74
    phasis
    0.72
     emphasis
    0.72
     ç¥ŀ
    0.70
     THANK
    0.67
    bold
    0.66
     lucky
    0.66
    Act Density 0.303%

    No Known Activations