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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing texture or feel, particularly focusing on words describing a soft or delicate texture

    oai_token-act-pair · gpt-3.5-turbo

    words related to texture or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEA
    -0.75
    RF
    -0.73
    ajor
    -0.73
    roit
    -0.72
    itutional
    -0.71
    rait
    -0.71
    krit
    -0.67
    channelAvailability
    -0.66
    )].
    -0.65
    LEASE
    -0.64
    POSITIVE LOGITS
    ness
    0.98
     eyed
    0.97
     sounding
    0.89
    glers
    0.85
    nesses
    0.83
     bits
    0.82
    bye
    0.81
     little
    0.80
     enough
    0.80
     slopes
    0.77
    Act Density 0.111%

    No Known Activations