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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts related to performance or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Macros
    -0.17
    inen
    -0.16
     Ign
    -0.15
    cona
    -0.15
     waited
    -0.14
    743
    -0.14
    oplevel
    -0.14
    ibold
    -0.14
     Bauer
    -0.14
    IOS
    -0.13
    POSITIVE LOGITS
    fall
    0.25
     fall
    0.23
     FALL
    0.23
     actually
    0.23
     falls
    0.21
    Fall
    0.21
     Fall
    0.21
     Actually
    0.21
     Sol
    0.20
    actually
    0.20
    Act Density 0.025%

    No Known Activations