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

    Neuronpedia

    INDEX
    Explanations

    terms related to degradation or stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manteau
    -0.52
    pigeon
    -0.49
    DrawerToggle
    -0.49
    Hentet
    -0.48
    onOptions
    -0.48
     Cutler
    -0.48
    DoS
    -0.48
    JPanel
    -0.47
     Kondo
    -0.47
    Pigeon
    -0.47
    POSITIVE LOGITS
     Hus
    0.67
    Hus
    0.60
    stable
    0.58
     stable
    0.57
    Stable
    0.56
     stabili
    0.53
     Stable
    0.52
    Laurence
    0.51
     stabilized
    0.51
    stabili
    0.50
    Act Density 0.509%

    No Known Activations