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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ControllerTest
    -0.57
    tometer
    -0.51
    PostExecute
    -0.47
    PullParser
    -0.47
    кож
    -0.47
    تفصیلات
    -0.45
    〗
    -0.45
     StringTokenizer
    -0.45
    互联网档案馆
    -0.45
     Jacobi
    -0.44
    POSITIVE LOGITS
     happen
    2.83
     happens
    2.59
     happened
    2.55
     happening
    2.35
    happen
    2.27
     Happen
    2.20
    happens
    2.16
    happened
    2.08
     HAPP
    2.06
     Happens
    2.02
    Act Density 0.235%

    No Known Activations