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

    Neuronpedia

    INDEX
    Explanations

    references to time and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
    -0.66
     myſelf
    -0.60
    PerformLayout
    -0.60
    DockStyle
    -0.60
    ſelves
    -0.59
     itſelf
    -0.57
    kloped
    -0.55
     pleaſure
    -0.53
     themſelves
    -0.53
    POSITIVE LOGITS
     time
    2.67
    time
    2.06
     Time
    2.00
    Time
    1.92
     TIME
    1.88
    TIME
    1.62
     tijd
    1.53
    时间
    1.41
     czasu
    1.36
     tiempo
    1.34
    Act Density 0.130%

    No Known Activations