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

    Neuronpedia

    INDEX
    Explanations

    text related to items of high value or importance

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.88
    wright
    -0.69
    ischer
    -0.69
     Judith
    -0.68
    odcast
    -0.68
    isco
    -0.67
    uca
    -0.66
     Ezek
    -0.66
     1954
    -0.65
    ooked
    -0.65
    POSITIVE LOGITS
    romeda
    0.87
     baggage
    0.84
     configurations
    0.82
     subsequ
    0.81
     cumbers
    0.81
     hence
    0.78
     resources
    0.77
     consequently
    0.77
     adaptations
    0.74
     thous
    0.74
    Act Density 0.402%

    No Known Activations