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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reactions and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.48
    ConfigureAwait
    -0.48
     Midway
    -0.46
     betweenstory
    -0.40
     Deposits
    -0.40
    ⎦
    -0.40
     AssemblyTitle
    -0.39
    otheses
    -0.39
    Deposits
    -0.39
     Psalm
    -0.39
    POSITIVE LOGITS
     react
    0.70
     act
    0.61
     attraction
    0.60
     choice
    0.56
     prize
    0.54
     attractions
    0.49
     reactions
    0.48
    InstrumentedTest
    0.48
     wealth
    0.48
    Życiorys
    0.47
    Act Density 0.229%

    No Known Activations