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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or existence of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uten
    -0.15
    iz
    -0.15
    ille
    -0.14
    aterno
    -0.14
    thon
    -0.14
    atura
    -0.14
     discredit
    -0.14
    xic
    -0.13
    eb
    -0.13
    ught
    -0.13
    POSITIVE LOGITS
    entially
    0.25
    ential
    0.20
    äºİ
    0.19
     existence
    0.17
    bjerg
    0.17
    entials
    0.17
     exists
    0.16
     Exists
    0.16
    ÏįÏĢ
    0.15
    bam
    0.15
    Act Density 0.059%

    No Known Activations