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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the concept of "soaking" or "absorption."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to soaking or saturation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eways
    -0.80
    axies
    -0.79
    affer
    -0.77
    atorial
    -0.75
     projection
    -0.71
    itars
    -0.70
     misunder
    -0.69
     suicidal
    -0.67
     rink
    -0.66
     submar
    -0.66
    POSITIVE LOGITS
    LECT
    0.92
     soak
    0.90
    lite
    0.84
    uncture
    0.75
    ersion
    0.75
    Micro
    0.73
     soaking
    0.71
    seq
    0.71
    hene
    0.71
    ffee
    0.69
    Act Density 0.014%

    No Known Activations