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

    Neuronpedia

    INDEX
    Explanations

    sentences about training animals using operant conditioning

    oai_token-act-pair · gemini-2.0-flash

    positive reinforcement concepts

    np_token-act-pair-logits · gpt-4o-mini

    positive reinforcement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.79
    Portail
    -0.73
    MigrationBuilder
    -0.61
     themſelves
    -0.58
    WebElementEntity
    -0.57
     newBuilder
    -0.55
     économies
    -0.54
     supérieurs
    -0.53
    Survivors
    -0.52
     ainfi
    -0.52
    POSITIVE LOGITS
     positive
    0.62
     Positive
    0.57
     conting
    0.55
    Positive
    0.55
     positively
    0.54
    rein
    0.54
     reward
    0.52
     Verstär
    0.51
     POSITIVE
    0.50
     bribery
    0.50
    Act Density 2.107%

    No Known Activations