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

    Neuronpedia

    INDEX
    Explanations

    statements and phrases relating to drawing conclusions and making assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TRAB
    -0.37
    nachweis
    -0.36
    TextFormField
    -0.34
    шены
    -0.33
     Simply
    -0.33
     ăn
    -0.32
    FTFY
    -0.31
    DEAR
    -0.31
    Constraint
    -0.31
    mögens
    -0.31
    POSITIVE LOGITS
     conclusion
    0.77
     decision
    0.73
     conclusions
    0.72
     conclude
    0.71
     decisions
    0.71
     judgment
    0.71
    判斷
    0.67
     decide
    0.66
     judgement
    0.66
    判断
    0.64
    Act Density 0.713%

    No Known Activations