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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal or technical language, particularly in academic or sophisticated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancellor
    -0.16
     createSelector
    -0.15
     stamp
    -0.15
    iere
    -0.15
    zes
    -0.14
    CASCADE
    -0.14
    æķ´
    -0.14
    rita
    -0.14
    angs
    -0.14
    recated
    -0.13
    POSITIVE LOGITS
     volupt
    0.28
     architect
    0.28
     dol
    0.25
     repell
    0.25
     commod
    0.25
     provid
    0.25
     fug
    0.24
     ration
    0.24
     ips
    0.24
     rep
    0.23
    Act Density 0.018%

    No Known Activations