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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with "with"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EClass
    -0.95
    ConstraintMaker
    -0.89
    ThroughAttribute
    -0.84
    MethodManager
    -0.84
    llary
    -0.82
    @@@@@@@@
    -0.80
    oredCriteria
    -0.80
     JAXB
    -0.79
     nonatomic
    -0.79
    Scénario
    -0.78
    POSITIVE LOGITS
     a
    0.51
     _$
    0.51
     McGovern
    0.45
    deque
    0.43
     hot
    0.43
    deck
    0.42
    lidos
    0.42
    ger
    0.41
    はじ
    0.41
    $
    0.41
    Act Density 0.032%

    No Known Activations