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

    Neuronpedia

    INDEX
    Explanations

    references to specific names such as "Axel" and "Dob"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the last name "Dob" or "Ack."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.78
    ĪĴ
    -0.73
    tics
    -0.69
    âĶĢâĶĢ
    -0.67
    ance
    -0.66
    */(
    -0.65
     vigil
    -0.63
     ILCS
    -0.63
    士
    -0.63
    thouse
    -0.62
    POSITIVE LOGITS
    hod
    0.89
    raf
    0.81
    itating
    0.79
    wana
    0.78
    ulous
    0.78
    rod
    0.77
    abee
    0.76
    rite
    0.75
    orno
    0.75
    ITAL
    0.74
    Act Density 0.035%

    No Known Activations