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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to principles or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪØ·
    -0.18
    gie
    -0.18
    reat
    -0.16
    elian
    -0.16
    akan
    -0.16
    ney
    -0.15
    eat
    -0.15
    arrant
    -0.15
     Airways
    -0.14
    quisition
    -0.14
    POSITIVE LOGITS
    -agent
    0.31
    ities
    0.25
     investigator
    0.23
    ps
    0.21
     Investig
    0.21
    /pr
    0.20
    -Agent
    0.20
    pal
    0.19
    stown
    0.18
     investigators
    0.18
    Act Density 0.019%

    No Known Activations