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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data collection and analysis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agues
    -0.18
    rig
    -0.16
     aggression
    -0.16
    enze
    -0.16
    iggins
    -0.15
    etros
    -0.15
    ovky
    -0.15
    rogen
    -0.15
    eres
    -0.15
    legacy
    -0.15
    POSITIVE LOGITS
    ging
    0.50
    ged
    0.48
    gy
    0.42
    gers
    0.41
    gle
    0.37
    gings
    0.37
    ger
    0.36
    gie
    0.35
    gs
    0.32
    gin
    0.32
    Act Density 0.490%

    No Known Activations