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

    Neuronpedia

    INDEX
    Explanations

    phrases related to buildings or structures with the word "house" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "house."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.78
    umbo
    -0.75
    ombie
    -0.71
    TAG
    -0.70
     DPR
    -0.70
     GOODMAN
    -0.69
     timelines
    -0.67
     Username
    -0.66
     mell
    -0.64
    dyl
    -0.63
    POSITIVE LOGITS
    wife
    1.08
    door
    1.02
    wives
    1.02
    hold
    1.00
    holders
    0.95
    keeping
    0.87
    holder
    0.85
    warming
    0.82
     cleaners
    0.79
    plate
    0.78
    Act Density 0.017%

    No Known Activations