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

    Neuronpedia

    INDEX
    Explanations

    references to legal responsibilities and agreements between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enberg
    -0.16
    cano
    -0.15
    anol
    -0.14
    opia
    -0.14
    ableObject
    -0.14
    levator
    -0.14
    INVAL
    -0.14
    porter
    -0.14
    eria
    -0.14
    shm
    -0.14
    POSITIVE LOGITS
     acting
    0.30
     agent
    0.26
     agents
    0.24
    acting
    0.24
     officers
    0.21
     officer
    0.20
     Acting
    0.19
     Agents
    0.19
    Named
    0.19
     authorized
    0.19
    Act Density 0.160%

    No Known Activations