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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions, particularly those involving inequalities and complex relationships in proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimés
    -0.62
    tagHelperRunner
    -0.60
     onBind
    -0.55
    IContainer
    -0.53
    providedIn
    -0.51
    Portail
    -0.49
    MLLoader
    -0.49
    zco
    -0.48
    酌
    -0.48
    SharedCtor
    -0.46
    POSITIVE LOGITS
     holds
    0.99
     hold
    0.91
     implies
    0.86
     Holds
    0.86
    holds
    0.83
     Hold
    0.82
     imply
    0.80
     HOLD
    0.76
     statement
    0.74
     implique
    0.74
    Act Density 1.919%

    No Known Activations