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

    Neuronpedia

    INDEX
    Explanations

    expressions and discussions related to critical thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.69
     ideals
    -0.48
     Stimmung
    -0.40
    SharedCtor
    -0.40
     snippetHide
    -0.40
     öner
    -0.40
     princípios
    -0.39
     nahilalakip
    -0.39
     mał
    -0.39
     caixa
    -0.38
    POSITIVE LOGITS
     think
    1.96
     thinking
    1.92
    think
    1.85
     Think
    1.81
    Think
    1.80
     THINK
    1.79
    thinking
    1.73
     Thinking
    1.71
    Thinking
    1.68
     thinks
    1.66
    Act Density 0.235%

    No Known Activations