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

    Neuronpedia

    INDEX
    Explanations

    terms related to counterfactual reasoning or alternative scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.75
     estekak
    -0.66
     referrerpolicy
    -0.65
     doInBackground
    -0.58
    ########.
    -0.57
     <=",
    -0.57
    SerializedName
    -0.55
    CppMethod
    -0.54
    cerely
    -0.53
    colhead
    -0.53
    POSITIVE LOGITS
    intuitive
    0.90
    productive
    0.80
    clockwise
    0.76
     intuitive
    0.75
    intu
    0.74
    vailing
    0.68
     intuitively
    0.67
     clockwise
    0.67
    balance
    0.66
     productive
    0.64
    Act Density 0.231%

    No Known Activations