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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Mother."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mother" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.75
    ript
    -0.74
     WATCHED
    -0.70
    ickr
    -0.67
    aping
    -0.67
    ahime
    -0.67
    oola
    -0.66
    aneously
    -0.65
    NRS
    -0.65
    jriwal
    -0.64
    POSITIVE LOGITS
     Mother
    0.87
     Teresa
    0.80
    heses
    0.78
    hood
    0.78
    Father
    0.77
    hesis
    0.74
    pring
    0.73
    ship
    0.73
     Father
    0.72
     Earth
    0.72
    Act Density 0.047%

    No Known Activations