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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating degrees of change or variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slightly
    -0.16
    ncy
    -0.15
    pen
    -0.15
    cko
    -0.15
    ken
    -0.14
     somewhat
    -0.14
    chnitt
    -0.14
    ouch
    -0.14
    795
    -0.13
    167
    -0.13
    POSITIVE LOGITS
    upon
    0.18
     compared
    0.17
     further
    0.17
    FAST
    0.17
    -fold
    0.16
    ">//
    0.16
    fold
    0.15
    UserCode
    0.15
    IRTH
    0.15
     more
    0.14
    Act Density 0.022%

    No Known Activations