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

    Neuronpedia

    INDEX
    Explanations

    references to agents in various contexts, particularly in scientific or technical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    humanité
    -0.46
    éclairage
    -0.42
    CppCodeGen
    -0.42
    épaisseur
    -0.40
     gynhyrchwyd
    -0.40
     soldadura
    -0.40
     tarde
    -0.40
     capucha
    -0.40
     Survival
    -0.39
     supervivencia
    -0.39
    POSITIVE LOGITS
     agent
    0.99
     Agent
    0.96
    Agent
    0.85
     agents
    0.85
    agent
    0.83
     AGENT
    0.82
    agents
    0.70
     Agents
    0.69
     atom
    0.68
    Agents
    0.67
    Act Density 0.310%

    No Known Activations