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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures and terms related to history or philosophy

    oai_token-act-pair · gpt-3.5-turbo

    references to influential historical figures and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDA
    -0.84
    aspx
    -0.81
    usercontent
    -0.81
    SHARE
    -0.79
    taboola
    -0.77
    AMI
    -0.76
    wx
    -0.73
    SPA
    -0.73
    hap
    -0.70
    Brow
    -0.70
    POSITIVE LOGITS
     famously
    1.13
     philosopher
    1.03
     aph
    0.97
     famous
    0.96
     prophetic
    0.96
     1896
    0.95
     seminal
    0.93
     dict
    0.92
     Nobel
    0.91
     coined
    0.91
    Act Density 0.661%

    No Known Activations