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

    Neuronpedia

    INDEX
    Explanations

    words related to competitions and rankings

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competitive group contexts and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.65
     Sterling
    -0.65
    _(
    -0.63
    hyde
    -0.63
     inconven
    -0.62
     psychiat
    -0.62
     proc
    -0.60
     breeze
    -0.60
    vable
    -0.60
     confidentiality
    -0.59
    POSITIVE LOGITS
    lishes
    0.77
     guiActiveUnfocused
    0.77
    urat
    0.73
    uces
    0.72
    outh
    0.70
    roups
    0.70
    together
    0.69
     consisting
    0.69
    ãĤ¤ãĥĪ
    0.68
    affiliated
    0.68
    Act Density 0.569%

    No Known Activations