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

    Neuronpedia

    INDEX
    Explanations

    references to "house" or similar dwelling-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zym
    -0.18
    owa
    -0.17
    ت
    -0.16
    ादन
    -0.16
     housed
    -0.16
    theless
    -0.16
    llum
    -0.15
    thic
    -0.15
    atically
    -0.15
    thal
    -0.15
    POSITIVE LOGITS
    wives
    0.32
    keeping
    0.31
    wares
    0.31
    wife
    0.31
    boat
    0.30
    guest
    0.29
    boats
    0.26
    mates
    0.26
    holds
    0.25
    mate
    0.25
    Act Density 0.063%

    No Known Activations