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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific structural or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.86
     becauſe
    -0.74
     Theſe
    -0.71
     Houſe
    -0.71
     متعلقه
    -0.70
    Referanser
    -0.68
     Efq
    -0.68
    lasses
    -0.65
     Akismet
    -0.65
    leſs
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.71
    principalTable
    0.65
     '\\;'
    0.64
    .
    0.55
     gereken
    0.53
     hombro
    0.51
     trataba
    0.48
    enerys
    0.47
    fjspx
    0.47
    InputTagHelper
    0.46
    Act Density 0.170%

    No Known Activations