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

    Neuronpedia

    INDEX
    Explanations

    terms related to updates or changes in documents and revisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.48
    мені
    -0.47
    _{*
    -0.46
     K
    -0.46
    DoubleQuotes
    -0.45
     R
    -0.43
     solidar
    -0.43
    포
    -0.43
     municipale
    -0.42
     alla
    -0.42
    POSITIVE LOGITS
     revise
    1.83
     revisions
    1.83
     revision
    1.79
     tweak
    1.78
     revising
    1.75
     modify
    1.74
     tweaking
    1.73
     Modify
    1.71
     modification
    1.68
     alteration
    1.67
    Act Density 0.206%

    No Known Activations