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

    Neuronpedia

    INDEX
    Explanations

    terms related to various projects, programs, schemes, and systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various projects, systems, and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.83
    ilaterally
    -0.75
    borgh
    -0.66
     Marketable
    -0.64
     Metallic
    -0.64
    soever
    -0.63
     Flavoring
    -0.63
    plet
    -0.63
     sqor
    -0.63
    ¢
    -0.62
    POSITIVE LOGITS
     itself
    0.96
     revolves
    0.86
     operates
    0.82
     underwent
    0.80
     lasted
    0.80
     culmin
    0.77
     consists
    0.76
     consisted
    0.76
     operator
    0.76
     began
    0.75
    Act Density 0.420%

    No Known Activations