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

    Neuronpedia

    INDEX
    Explanations

    and highlight pieces of information that have been officially recorded or noted down in detail

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of documenting events or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.81
    ners
    -0.76
    les
    -0.74
    govtrack
    -0.72
    committee
    -0.70
    bite
    -0.70
    bit
    -0.70
    bies
    -0.69
    esta
    -0.67
    oldemort
    -0.66
    POSITIVE LOGITS
     feats
    0.83
    ocument
    0.82
     documenting
    0.79
     firsthand
    0.76
    REAM
    0.74
     evid
    0.69
     Record
    0.67
     documented
    0.67
    IDENT
    0.65
    ĸļ
    0.65
    Act Density 0.043%

    No Known Activations