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

    Neuronpedia

    INDEX
    Explanations

    actions or instructions involving covering, wrapping, or overlaying objects

    oai_token-act-pair · gpt-3.5-turbo

    references to materials and coverings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incarn
    -0.76
    IGHTS
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    qual
    -0.69
    ceans
    -0.67
     resurg
    -0.67
    ãĤŃ
    -0.67
    ACTED
    -0.66
    undown
    -0.66
    Contin
    -0.65
    POSITIVE LOGITS
     covering
    0.94
     wrap
    0.93
     coated
    0.89
     securely
    0.86
     protr
    0.85
    cloth
    0.85
     encl
    0.84
     layer
    0.84
     thickness
    0.84
     insulation
    0.84
    Act Density 0.221%

    No Known Activations