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

    Neuronpedia

    INDEX
    Explanations

    references to a figure of authority or parental figure

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "addy" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.79
     subsequ
    -0.75
     satell
    -0.75
     skelet
    -0.73
     mathemat
    -0.72
     carbohyd
    -0.72
     prototyp
    -0.69
    ELL
    -0.68
     warr
    -0.68
     fortun
    -0.67
    POSITIVE LOGITS
    addy
    1.15
    wagon
    0.85
    emonic
    0.81
    Boss
    0.75
    qs
    0.71
    cakes
    0.68
    fields
    0.68
    fw
    0.67
    boss
    0.66
    ire
    0.66
    Act Density 0.055%

    No Known Activations