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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Happ
    -0.15
    reater
    -0.14
    ungi
    -0.14
    ÙĪرت
    -0.14
    以ä¸Ĭ
    -0.14
    нÑĸÑĪе
    -0.14
    perms
    -0.14
    auer
    -0.13
    941
    -0.13
    SEMB
    -0.13
    POSITIVE LOGITS
     SUCH
    0.28
     such
    0.28
    Such
    0.23
    such
    0.22
     Such
    0.21
     my
    0.20
     definitely
    0.20
     honestly
    0.19
     similar
    0.19
     very
    0.17
    Act Density 0.148%

    No Known Activations