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

    Neuronpedia

    INDEX
    Explanations

    mathematical comparisons and relationships between numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.59
     يتيمه
    -0.54
    YMMV
    -0.53
    featureID
    -0.53
    BuilderFactory
    -0.53
     típica
    -0.51
    меч
    -0.51
     typique
    -0.51
     ~
    -0.51
     turisti
    -0.51
    POSITIVE LOGITS
     minus
    1.22
     plus
    1.20
     equals
    0.92
     equal
    0.91
    minus
    0.88
     zero
    0.84
     Plus
    0.83
    plus
    0.77
     times
    0.76
    Minus
    0.75
    Act Density 1.389%

    No Known Activations