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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that indicate contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -0.74
    PreferredItem
    -0.73
    ſelf
    -0.70
     zwiſchen
    -0.70
    SBATCH
    -0.70
    fromnode
    -0.69
    modity
    -0.69
     fubject
    -0.68
    WireFormatLite
    -0.66
     EdgeInsets
    -0.66
    POSITIVE LOGITS
     it
    0.46
     But
    0.38
     but
    0.37
    But
    0.37
    -
    0.35
    t
    0.33
     It
    0.33
     I
    0.32
    A
    0.32
     sûre
    0.32
    Act Density 0.238%

    No Known Activations