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

    Neuronpedia

    INDEX
    Explanations

    instances where numerical data points are connected by 'and'

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions related to statistical or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.91
    Synopsis
    -0.79
    insula
    -0.69
    yout
    -0.65
    Course
    -0.65
    mire
    -0.65
    ESE
    -0.65
    ÃĽ
    -0.64
    ocene
    -0.64
    gg
    -0.64
    POSITIVE LOGITS
     counting
    1.11
     56
    0.96
     374
    0.96
     57
    0.95
     36
    0.94
     58
    0.94
     averaged
    0.94
     66
    0.94
     680
    0.93
     37
    0.93
    Act Density 0.193%

    No Known Activations