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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the words 'hard' and 'fast'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to definitions and contrasting concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUn
    -0.91
    nostic
    -0.67
    VERTIS
    -0.67
    abre
    -0.67
    66666666
    -0.66
    apore
    -0.66
    =-=-=-=-=-=-=-=-
    -0.65
    mbuds
    -0.65
    {"
    -0.64
     UL
    -0.62
    POSITIVE LOGITS
     Bullets
    0.73
     bruising
    0.69
     weeds
    0.69
     Alto
    0.66
     âĶľ
    0.65
     abras
    0.65
     nails
    0.63
    grass
    0.63
    ãĥķãĤ¡
    0.62
     partisans
    0.61
    Act Density 0.128%

    No Known Activations