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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    adjectives indicating quantity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.69
    farious
    -0.68
    akespe
    -0.66
    emale
    -0.65
    edIn
    -0.64
    èĢ
    -0.61
     Vaugh
    -0.60
    stood
    -0.60
    tein
    -0.60
    ilaterally
    -0.58
    POSITIVE LOGITS
     Sexy
    0.61
     Vulkan
    0.59
    actionDate
    0.57
     Expand
    0.56
     Psy
    0.55
     âĢº
    0.54
    ICE
    0.52
     Steam
    0.51
    photos
    0.51
    âĦ¢:
    0.51
    Act Density 0.245%

    No Known Activations