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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references related to research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.63
    copg
    -0.54
    extAlignment
    -0.54
    ngths
    -0.52
    IntoConstraints
    -0.51
    ricular
    -0.51
     nahilalakip
    -0.50
     CURIAM
    -0.48
     "','
    -0.48
    hoeddwyd
    -0.48
    POSITIVE LOGITS
     Issue
    0.47
     issue
    0.47
    Issue
    0.44
    issue
    0.42
     No
    0.39
    adaptiveStyles
    0.38
     Issues
    0.38
    No
    0.36
    Issues
    0.36
    Rohy
    0.36
    Act Density 0.605%

    No Known Activations