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

    Neuronpedia

    INDEX
    Explanations

    names of various types of companies

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of organizations and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positives
    -0.70
     Tanks
    -0.70
     Machines
    -0.65
    ãĥĥãĥī
    -0.64
     Blades
    -0.63
     Goo
    -0.61
    headers
    -0.61
    othy
    -0.60
    ynes
    -0.60
     Demons
    -0.60
    POSITIVE LOGITS
     specializing
    0.89
     called
    0.85
     Called
    0.85
    rador
    0.80
     classmate
    0.78
     named
    0.73
    load
    0.73
     whose
    0.72
     staffed
    0.69
    mate
    0.69
    Act Density 0.330%

    No Known Activations