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

    Neuronpedia

    INDEX
    Explanations

    words associated with social problems and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licts
    -0.17
    licas
    -0.17
    waters
    -0.16
    -rays
    -0.16
    ovies
    -0.15
    udicots
    -0.15
    -offs
    -0.15
    oters
    -0.15
    -fields
    -0.15
    brates
    -0.15
    POSITIVE LOGITS
    omaly
    0.19
    uger
    0.17
    {}_
    0.15
    /pm
    0.15
    odule
    0.15
    ivist
    0.15
    FFE
    0.15
    sphere
    0.15
    league
    0.14
    isphere
    0.14
    Act Density 0.499%

    No Known Activations