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

    Neuronpedia

    INDEX
    Explanations

    prepositions and other short function words

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference various aspects and features of products or creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olitical
    -0.65
    national
    -0.63
    oliberal
    -0.62
    ATIONAL
    -0.61
    ullah
    -0.59
    osate
    -0.58
    OGR
    -0.57
    uania
    -0.57
    zbollah
    -0.56
    ouched
    -0.56
    POSITIVE LOGITS
     sorts
    0.72
     ours
    0.65
     this
    0.65
     those
    0.64
     these
    0.62
     theirs
    0.61
     what
    0.61
     wanting
    0.60
     yours
    0.60
     our
    0.59
    Act Density 0.844%

    No Known Activations