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

    Neuronpedia

    INDEX
    Explanations

    descriptions of processes or methods for achieving desired outcomes or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.60
    rawDesc
    -0.57
    iastes
    -0.52
     SDLK
    -0.51
    ScopeManager
    -0.50
    RuleContext
    -0.46
    addPreferredGap
    -0.46
    endphp
    -0.43
    agrama
    -0.43
     roomId
    -0.43
    POSITIVE LOGITS
     they
    0.64
     we
    0.62
     you
    0.56
     people
    0.51
     it
    0.49
     he
    0.48
     HOW
    0.48
     how
    0.45
     BoxFit
    0.42
     physicians
    0.41
    Act Density 0.298%

    No Known Activations