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

    Neuronpedia

    INDEX
    Explanations

    the word "ranking" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hierarchical positions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jab
    -0.87
    panic
    -0.76
    argo
    -0.74
    gm
    -0.71
    ported
    -0.70
    idem
    -0.68
     Apocalypse
    -0.68
    RPG
    -0.67
    ario
    -0.65
    primary
    -0.64
    POSITIVE LOGITS
     ranking
    1.06
     rankings
    0.93
    Rank
    0.91
     Ranking
    0.85
    hyde
    0.75
     rank
    0.74
     unbeliev
    0.74
     citiz
    0.73
    ranked
    0.73
     ranked
    0.73
    Act Density 0.005%

    No Known Activations