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

    Neuronpedia

    INDEX
    Explanations

    repetitive structures or patterns in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesel
    -0.21
    amak
    -0.15
    unj
    -0.15
    isoft
    -0.14
    odash
    -0.14
    út
    -0.14
    _exempt
    -0.14
    ught
    -0.14
    arpa
    -0.14
    ะ
    -0.14
    POSITIVE LOGITS
    ifications
    0.26
    ifi
    0.24
    ifiable
    0.23
    ifying
    0.22
    ifies
    0.19
    ification
    0.19
    ified
    0.18
    IFI
    0.17
    sand
    0.16
    s
    0.16
    Act Density 0.113%

    No Known Activations