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

    Neuronpedia

    INDEX
    Explanations

    references to significant figures and elements related to height or physical dimensions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wires
    -0.53
    oflavin
    -0.52
    rxjs
    -0.52
     BehaviorSubject
    -0.52
     bande
    -0.48
     wire
    -0.48
    point
    -0.47
     dart
    -0.47
     wits
    -0.47
     feathers
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.97
     mammoth
    0.96
     gigantic
    0.94
     behe
    0.90
     géant
    0.90
     gigante
    0.89
     gigantes
    0.88
    UnusedPrivate
    0.88
    Giant
    0.87
     giant
    0.87
    Act Density 0.562%

    No Known Activations