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

    Neuronpedia

    INDEX
    Explanations

    terms related to failure probabilities and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    failure and its outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ober
    -0.31
     Targ
    -0.31
    IVIA
    -0.30
    PopupMenu
    -0.30
     Wrang
    -0.30
     eyeing
    -0.29
     Volo
    -0.29
     savvy
    -0.29
    tahui
    -0.29
     Men
    -0.29
    POSITIVE LOGITS
     failure
    1.55
     Failure
    1.46
     failing
    1.36
    failure
    1.36
     failures
    1.35
    Failure
    1.32
     failed
    1.28
     fail
    1.28
     Failures
    1.27
    Failing
    1.27
    Act Density 0.069%

    No Known Activations