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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ary
    -0.52
     fe
    -0.47
     =>
    -0.47
    esa
    -0.45
    dite
    -0.45
     ass
    -0.44
    ata
    -0.43
    esch
    -0.42
    bige
    -0.42
    )$/,
    -0.42
    POSITIVE LOGITS
    ſelves
    0.93
     myſelf
    0.93
    ValueStyle
    0.92
    ConstraintMaker
    0.91
    ſelf
    0.90
     Houſe
    0.88
     pleaſure
    0.86
     esternos
    0.85
     himſelf
    0.85
     Monfieur
    0.84
    Act Density 0.631%

    No Known Activations