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

    Neuronpedia

    INDEX
    Explanations

    terms related to journalism and media

    oai_token-act-pair · gpt-3.5-turbo

    terms related to journalism and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.69
     dreaded
    -0.68
     Atlantis
    -0.66
     habitable
    -0.65
    ographed
    -0.63
    ãĥ¯ãĥ³
    -0.62
    ificantly
    -0.62
    Important
    -0.62
    amous
    -0.61
     piping
    -0.60
    POSITIVE LOGITS
    vironments
    0.87
    smanship
    0.73
    secution
    0.68
    ystem
    0.68
    ounters
    0.67
    alloc
    0.66
    ivism
    0.66
    "}],"
    0.66
    rencies
    0.66
    agonist
    0.65
    Act Density 0.675%

    No Known Activations