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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data or quantitative comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.49
    ...
    -0.46
    0
    -0.45
     \
    -0.43
     a
    -0.43
     some
    -0.42
    6
    -0.42
    iconCls
    -0.41
     -
    -0.40
     «
    -0.40
    POSITIVE LOGITS
     pleaſure
    1.20
     houſe
    1.07
     Efq
    1.00
     ſtate
    1.00
     Chriftian
    0.96
     myſelf
    0.93
     Houſe
    0.92
     cauſe
    0.92
     Shakspeare
    0.89
     Monfieur
    0.89
    Act Density 1.471%

    No Known Activations