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

    Neuronpedia

    INDEX
    Explanations

    terms related to protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.09
     Theſe
    -0.86
     becauſe
    -0.83
     Diſ
    -0.80
     Jefus
    -0.78
     Eſ
    -0.77
     Monfieur
    -0.77
     fhew
    -0.76
     auroit
    -0.73
     renunciation
    -0.73
    POSITIVE LOGITS
     protocol
    1.76
     protocols
    1.75
     Protocol
    1.63
    Protocol
    1.48
     PROTOCOL
    1.45
     Protocols
    1.41
    protocol
    1.41
    Protocols
    1.32
    protocols
    1.23
     protocolo
    1.21
    Act Density 0.057%

    No Known Activations