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

    Neuronpedia

    INDEX
    Explanations

    references to specific names, especially "Cantor" and "imer"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Eric Cantor and related figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.97
    lihood
    -0.78
    versions
    -0.76
    cess
    -0.75
    leted
    -0.69
    iru
    -0.69
    licks
    -0.68
    char
    -0.67
    ition
    -0.67
    cer
    -0.66
    POSITIVE LOGITS
    agnar
    0.82
    dinand
    0.80
    daq
    0.80
    osal
    0.76
    noon
    0.75
    imer
    0.74
    agall
    0.74
     Tsarnaev
    0.72
    enment
    0.72
    eering
    0.71
    Act Density 0.030%

    No Known Activations