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

    Neuronpedia

    INDEX
    Explanations

    time-related words

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating recent events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.66
    ventions
    -0.65
    ellation
    -0.64
    pora
    -0.64
    selection
    -0.64
    multipl
    -0.63
    chwitz
    -0.63
    alam
    -0.63
    tre
    -0.62
    ross
    -0.62
    POSITIVE LOGITS
     avail
    0.65
     lasts
    0.63
    è¦
    0.61
    hig
    0.61
     lawy
    0.61
    ODY
    0.61
     appe
    0.60
     semblance
    0.60
    inally
    0.60
    iffe
    0.59
    Act Density 0.153%

    No Known Activations