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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases beginning with "of" followed by a high-frequency word

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions indicating relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphate
    -0.77
    igion
    -0.68
    earchers
    -0.67
    Quantity
    -0.66
    orsche
    -0.65
     teasp
    -0.65
    thood
    -0.64
    apons
    -0.63
    pmwiki
    -0.62
    soever
    -0.62
    POSITIVE LOGITS
     his
    0.92
     excerpts
    0.91
     this
    0.90
     these
    0.87
     Spicer
    0.82
     Wednesday
    0.82
     HuffPost
    0.81
     those
    0.80
     Tuesday
    0.80
     the
    0.79
    Act Density 0.449%

    No Known Activations