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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for words related to layers or boundaries of objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the "outer" layers or boundaries of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essors
    -0.78
    inators
    -0.74
    inatory
    -0.74
    inator
    -0.74
    netflix
    -0.73
    Pitt
    -0.72
    bley
    -0.71
    anwhile
    -0.71
    HCR
    -0.71
    utes
    -0.70
    POSITIVE LOGITS
    most
    1.31
    wear
    1.01
     casing
    0.85
     circumference
    0.85
    worldly
    0.84
    borough
    0.84
     diameter
    0.83
     garments
    0.79
     bounds
    0.79
     extrem
    0.77
    Act Density 0.012%

    No Known Activations