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

    Neuronpedia

    INDEX
    Explanations

    objects commonly associated with home decoration and repair

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of lamps and lighting fixtures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulate
    -0.74
    088
    -0.70
    remlin
    -0.66
    Relations
    -0.64
    CHO
    -0.64
    ESE
    -0.63
    JUST
    -0.63
    BLIC
    -0.62
    REDACTED
    -0.62
    059
    -0.61
    POSITIVE LOGITS
     lamp
    1.16
     Lamp
    1.11
     lamps
    0.94
     lantern
    0.94
     bulb
    0.88
    reys
    0.80
    oons
    0.77
     bulbs
    0.74
     Lantern
    0.74
     illum
    0.69
    Act Density 0.006%

    No Known Activations