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

    Neuronpedia

    INDEX
    Explanations

    unique characteristics and attributes related to identity and originality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acchi
    -0.41
    resizingMask
    -0.40
    ABASE
    -0.40
    Severity
    -0.38
    endphp
    -0.38
     ceram
    -0.38
    Capricorn
    -0.38
    eradish
    -0.38
    AddWithValue
    -0.36
     Bayes
    -0.36
    POSITIVE LOGITS
     unique
    3.13
    unique
    2.70
     Unique
    2.61
     uniqueness
    2.53
    Unique
    2.52
     UNIQUE
    2.41
     uniques
    2.31
     unieke
    2.25
     uniquely
    2.22
     уника
    2.22
    Act Density 0.814%

    No Known Activations