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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or prediction outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.53
    RuleContext
    -0.53
     understood
    -0.52
     favorably
    -0.51
    Thru
    -0.51
     favored
    -0.50
    recognized
    -0.50
    IntoConstraints
    -0.50
    Recognizer
    -0.49
    ChildScrollView
    -0.49
    POSITIVE LOGITS
    <?
    0.71
     pymysql
    0.64
    やっぱ
    0.61
    SourceChecksum
    0.61
     đạo
    0.60
    MenuGroup
    0.60
    WithIOException
    0.59
     Normdatei
    0.58
    OGND
    0.57
     tenté
    0.57
    Act Density 0.004%

    No Known Activations