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

    Neuronpedia

    INDEX
    Explanations

    mentions of clothing items such as blouses

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "house."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchangeable
    -0.69
     boulder
    -0.66
     distant
    -0.65
    ellen
    -0.64
     lumber
    -0.63
    icial
    -0.61
    igsaw
    -0.61
     recess
    -0.61
    schild
    -0.60
     sequest
    -0.59
    POSITIVE LOGITS
    ouse
    1.56
    oused
    1.10
    xual
    1.09
    ousing
    0.97
    ouses
    0.94
    manship
    0.89
    ktop
    0.88
    holders
    0.84
    meat
    0.82
    ItemTracker
    0.79
    Act Density 0.014%

    No Known Activations