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

    Neuronpedia

    INDEX
    Explanations

    contractions and phrases indicating temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лаÑĪ
    -0.15
    amarin
    -0.14
    emoc
    -0.14
    alles
    -0.14
    otec
    -0.13
     CSC
    -0.13
    orie
    -0.13
    ìĤ¬ëŀij
    -0.13
    ýn
    -0.13
     buggy
    -0.13
    POSITIVE LOGITS
     Stanley
    0.38
    Stan
    0.34
     Stan
    0.32
     stan
    0.31
     Bonnie
    0.27
    -↵
    0.23
     Bon
    0.22
    Bon
    0.21
     bon
    0.20
     Guid
    0.20
    Act Density 0.000%

    No Known Activations