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

    Neuronpedia

    INDEX
    Explanations

    terms related to interventions and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.48
     becauſe
    -0.42
     poffible
    -0.41
    这篇
    -0.39
     crossings
    -0.39
    dafx
    -0.38
    TagHelper
    -0.37
    págs
    -0.37
     juſ
    -0.37
     miſ
    -0.37
    POSITIVE LOGITS
    Intern
    0.71
    INTER
    0.71
    intern
    0.71
     intern
    0.69
     Intern
    0.69
     INTER
    0.68
     invitation
    0.60
     appointment
    0.59
    interp
    0.57
    Interpretation
    0.57
    Act Density 1.882%

    No Known Activations