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

    Neuronpedia

    INDEX
    Explanations

    references to terminals and terminal-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.70
     Timp
    -0.64
     disambiguazione
    -0.64
     pacchetto
    -0.63
     виправивши
    -0.63
     couvercle
    -0.61
     Houſe
    -0.59
    copg
    -0.57
     houſe
    -0.56
     contemporaine
    -0.54
    POSITIVE LOGITS
     retrieve
    0.86
     Retrieve
    0.79
     terminal
    0.76
     Retrieval
    0.74
     Terminal
    0.71
     Terminals
    0.69
    StructEnd
    0.68
     retrieved
    0.68
    GTCX
    0.68
    ..
    0.66
    Act Density 0.265%

    No Known Activations