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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "real" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.72
     Biôgrafia
    -0.69
    ContentAsync
    -0.66
    buttonShape
    -0.65
    lapi
    -0.64
     defaultstate
    -0.64
     utafitiHapana
    -0.61
    ErrUnexpectedEOF
    -0.59
     дописавши
    -0.58
    tanooga
    -0.58
    POSITIVE LOGITS
     realization
    1.32
     realized
    1.29
     realisation
    1.29
     realize
    1.28
     realise
    1.21
     realised
    1.20
     réalis
    1.20
     realizing
    1.20
     realizes
    1.18
     realising
    1.16
    Act Density 0.432%

    No Known Activations