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

    Neuronpedia

    INDEX
    Explanations

    various forms and usages of the word "to" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sabb
    -0.16
    nero
    -0.16
     uz
    -0.15
    /sbin
    -0.14
    _INCLUDE
    -0.14
    stroy
    -0.14
    .social
    -0.14
    TL
    -0.13
    Authorized
    -0.13
    (BitConverter
    -0.13
    POSITIVE LOGITS
    纪
    0.17
     воÑĢ
    0.16
    iron
    0.15
    issa
    0.15
     along
    0.14
    xfd
    0.14
    nton
    0.14
    aled
    0.14
     Idol
    0.14
     alongside
    0.13
    Act Density 0.006%

    No Known Activations