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

    Neuronpedia

    INDEX
    Explanations

    mentions of quantities or numbers in structured contexts

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or contrasts to a greater degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.70
    ettel
    -0.70
    Merit
    -0.68
    pmwiki
    -0.68
    Asset
    -0.66
    âĵĺ
    -0.66
    pload
    -0.65
    ythm
    -0.63
     Logged
    -0.63
    acci
    -0.63
    POSITIVE LOGITS
     English
    0.57
     Western
    0.55
     physical
    0.54
     British
    0.54
     geographically
    0.53
     latter
    0.52
     Swedish
    0.52
     hypothetical
    0.52
     newspaper
    0.52
     intellectual
    0.51
    Act Density 2.055%

    No Known Activations