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

    Neuronpedia

    INDEX
    Explanations

    opening or starting tokens in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tener
    -0.65
    SBATCH
    -0.65
     sved
    -0.62
    {{/
    -0.62
     Vettel
    -0.62
    pherals
    -0.61
    MLLoader
    -0.61
     Barbar
    -0.60
    -0.59
    ViewStyle
    -0.58
    POSITIVE LOGITS
    mi
    2.23
    MI
    1.43
     mi
    1.25
     Mi
    1.22
    Mi
    1.22
    OMI
    1.19
     MI
    1.16
     Ami
    1.00
    AMI
    0.99
    Ami
    0.97
    Act Density 0.040%

    No Known Activations