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

    Neuronpedia

    INDEX
    Explanations

    references to machines and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.52
     Efq
    -1.52
     Monfieur
    -1.48
     myſelf
    -1.44
     Theſe
    -1.41
     houſe
    -1.41
     Houſe
    -1.40
     Jefus
    -1.39
     ſtate
    -1.34
     auroit
    -1.34
    POSITIVE LOGITS
     machines
    1.19
    machines
    1.04
     Machines
    0.89
     
    0.85
    Machines
    0.82
     machinery
    0.80
     (
    0.74
     Cor
    0.73
     br
    0.73
     for
    0.73
    Act Density 0.211%

    No Known Activations