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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific person, possibly related to sports or media

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "son" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptions
    -0.79
    arded
    -0.78
    hered
    -0.69
    PER
    -0.61
    odies
    -0.59
    ASED
    -0.59
     deficits
    -0.58
    enance
    -0.56
    grades
    -0.56
     probing
    -0.56
    POSITIVE LOGITS
    ics
    0.87
    nen
    0.86
    ja
    0.79
    earth
    0.78
    ville
    0.78
    nel
    0.77
    nette
    0.76
    alia
    0.75
    strom
    0.74
    emouth
    0.74
    Act Density 0.048%

    No Known Activations