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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of control or dominance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ran" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĢIJ
    -0.76
    ĨĴ
    -0.75
    GMT
    -0.68
    £ı
    -0.67
     sparse
    -0.65
    ITNESS
    -0.65
    EMP
    -0.65
     perfect
    -0.64
     overdue
    -0.63
     Holden
    -0.63
    POSITIVE LOGITS
    igans
    1.09
    vier
    1.05
    ran
    1.03
    igan
    0.95
    quez
    0.92
    stal
    0.91
    zan
    0.85
    tenance
    0.85
    fo
    0.85
    rome
    0.81
    Act Density 0.010%

    No Known Activations