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

    Neuronpedia

    INDEX
    Explanations

    instances of replacement and transformation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igel
    -0.16
    aho
    -0.15
    uno
    -0.15
    erk
    -0.14
    aro
    -0.14
    ahn
    -0.14
     éĬ
    -0.14
    erken
    -0.14
    aos
    -0.14
    oxel
    -0.13
    POSITIVE LOGITS
     ones
    0.20
     instead
    0.18
     yerine
    0.18
    leo
    0.17
    碼
    0.16
    zas
    0.15
    )new
    0.15
    instead
    0.15
    uju
    0.15
    寸
    0.15
    Act Density 0.146%

    No Known Activations