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

    Neuronpedia

    INDEX
    Explanations

    expressions related to individuals' interests and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MockMvc
    -0.49
    oas
    -0.48
    atimes
    -0.48
    ONAUT
    -0.48
    Hentet
    -0.47
     Ause
    -0.46
    ardoor
    -0.45
    ="@+
    -0.44
     Normdatei
    -0.43
     AssemblyTitle
    -0.42
    POSITIVE LOGITS
     interests
    1.70
     welfare
    1.46
     Interests
    1.44
    interests
    1.40
     interest
    1.29
    welfare
    1.18
     WELFARE
    1.12
    interest
    1.12
     benefit
    1.11
     Interest
    1.10
    Act Density 0.236%

    No Known Activations