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

    Neuronpedia

    INDEX
    Explanations

    textual structures indicating temporal relationships or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     terr
    -0.15
    urm
    -0.15
     ne
    -0.15
    utin
    -0.14
    -des
    -0.14
     Terr
    -0.14
    ulin
    -0.14
     Flake
    -0.14
    Separator
    -0.14
     Maid
    -0.14
    POSITIVE LOGITS
    zzo
    0.19
    IFA
    0.19
    ault
    0.15
    rana
    0.14
    __$
    0.14
     aalborg
    0.14
    夫人
    0.14
    deo
    0.14
    ież
    0.14
    ieder
    0.14
    Act Density 0.143%

    No Known Activations