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

    Neuronpedia

    INDEX
    Explanations

    the word "then" in various contexts, indicating a focus on sequential reasoning or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -1.12
    ſelves
    -1.07
    ſelf
    -1.05
    PerformLayout
    -1.04
     itſelf
    -1.04
     houſe
    -1.04
     Houſe
    -0.97
     Efq
    -0.97
     ―――――
    -0.95
     myſelf
    -0.95
    POSITIVE LOGITS
     it
    1.06
     we
    0.83
     the
    0.81
     I
    0.79
     you
    0.77
     there
    0.77
     they
    0.76
     
    0.74
     most
    0.68
     this
    0.68
    Act Density 0.040%

    No Known Activations