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

    Neuronpedia

    INDEX
    Explanations

    themes related to crime and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */].
    -0.58
    olism
    -0.55
     automatiques
    -0.54
     муніципалі
    -0.53
    letto
    -0.52
     Alamy
    -0.52
     برانيه
    -0.51
    ATIVES
    -0.50
     FontWeight
    -0.50
    etron
    -0.50
    POSITIVE LOGITS
    +:+
    0.60
     fail
    0.59
     admitting
    0.55
     fails
    0.55
    lgari
    0.54
     crumbling
    0.54
     admit
    0.52
     concedes
    0.51
     failed
    0.50
    RLock
    0.50
    Act Density 0.361%

    No Known Activations