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

    Neuronpedia

    INDEX
    Explanations

    boolean values and their associated attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mphony
    -0.60
    oyer
    -0.57
    hydra
    -0.56
    enfone
    -0.56
    msgTypes
    -0.56
    osit
    -0.55
     Waray
    -0.55
    nix
    -0.54
    Bibliography
    -0.54
    Группа
    -0.53
    POSITIVE LOGITS
    true
    2.44
     true
    2.09
    false
    1.96
    True
    1.91
    TRUE
    1.88
     TRUE
    1.78
     True
    1.76
     false
    1.65
    FALSE
    1.58
    False
    1.57
    Act Density 0.034%

    No Known Activations