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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egers
    -0.16
    owered
    -0.16
    ho
    -0.16
    IOC
    -0.16
     Ñģклад
    -0.15
    rok
    -0.15
    canf
    -0.14
    豪
    -0.14
    resar
    -0.14
    ä¸
    -0.14
    POSITIVE LOGITS
    mutable
    0.16
    _WR
    0.14
     silent
    0.14
    Äįem
    0.14
    eyin
    0.13
    ÏĦÏī
    0.13
    aks
    0.13
    ála
    0.13
    ;\↵
    0.13
    lek
    0.13
    Act Density 0.176%

    No Known Activations