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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or significant break in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.08
    ftagPool
    -0.97
    principalColumn
    -0.96
     CreateTagHelper
    -0.92
     مشين
    -0.92
     يتيمه
    -0.90
    tableFuture
    -0.90
     '\\;'
    -0.89
    antMatchers
    -0.87
    fjspx
    -0.86
    POSITIVE LOGITS
    ↵↵↵
    0.70
    <eos>
    0.68
    ↵↵
    0.59
    ↵↵↵↵
    0.58
     cérebro
    0.57
    A
    0.56
    вед
    0.56
    芙
    0.55
    With
    0.54
    ↵
    0.52
    Act Density 0.080%

    No Known Activations