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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing additional information or context

    oai_token-act-pair · gpt-3.5-turbo

    relative clauses that introduce additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulp
    -0.70
    uta
    -0.67
    bug
    -0.65
    hazard
    -0.65
    PORT
    -0.63
    Express
    -0.63
    Quantity
    -0.63
    anon
    -0.63
    air
    -0.63
    RNA
    -0.62
    POSITIVE LOGITS
    ophon
    0.83
     comprises
    0.75
     longest
    0.71
    ;;;;;;;;;;;;
    0.70
    soever
    0.70
     hailed
    0.70
    kinson
    0.70
    ãĥ¯
    0.68
    itars
    0.68
     oldest
    0.67
    Act Density 0.156%

    No Known Activations