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

    Neuronpedia

    INDEX
    Explanations

    propositions and conditions related to assumptions in a theoretical context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Mous
    -0.67
    ules
    -0.66
    oia
    -0.65
    ule
    -0.63
    ならず
    -0.61
     Miro
    -0.60
    umes
    -0.58
    ose
    -0.58
    <?
    -0.57
    ular
    -0.57
    POSITIVE LOGITS
    ruptedException
    0.67
    ptonshire
    0.66
     Assumptions
    0.63
    RegressionTest
    0.61
    ArgsConstructor
    0.61
     Numerade
    0.61
    RoutingModule
    0.60
     Assumption
    0.60
     "..\..\..\
    0.60
     UnityEditor
    0.59
    Act Density 0.019%

    No Known Activations