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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal indicators or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    838
    -0.17
    ãĥ³ãĥĩ
    -0.17
    eson
    -0.16
    çĿ
    -0.15
    Latch
    -0.15
    acket
    -0.15
    ALCHEMY
    -0.14
    alf
    -0.14
    жд
    -0.14
    alary
    -0.14
    POSITIVE LOGITS
     advances
    0.23
     advance
    0.21
     advancement
    0.20
     advanced
    0.20
     advancements
    0.19
     advancing
    0.17
     Advances
    0.17
     steal
    0.17
     Pom
    0.16
     stealing
    0.16
    Act Density 0.000%

    No Known Activations