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

    Neuronpedia

    INDEX
    Explanations

    Phrases related to quantity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to diverse experiences and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggle
    -0.51
    otonin
    -0.50
    Newsletter
    -0.49
    WAR
    -0.48
    iatus
    -0.46
    different
    -0.45
    Labor
    -0.45
     Background
    -0.45
     lately
    -0.45
    emporary
    -0.45
    POSITIVE LOGITS
     notwithstanding
    0.79
    conservancy
    0.62
     respectively
    0.59
     srf
    0.56
     thereof
    0.55
     etc
    0.52
     increments
    0.51
     comprom
    0.50
    onga
    0.49
    uably
    0.49
    Act Density 1.882%

    No Known Activations