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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "")
    -0.51
     sahaja
    -0.51
     tradisional
    -0.50
    -“
    -0.50
    .“
    -0.49
     quæ
    -0.46
     {};
    -0.46
     einst
    -0.46
     pianta
    -0.45
     vostri
    -0.45
    POSITIVE LOGITS
    ↵
    0.95
     //
    0.79
    casus
    0.69
     \%,
    0.63
    ________,
    0.62
     },
    0.62
    %',
    0.61
    %",
    0.61
     \%$,
    0.61
     ✔
    0.60
    Act Density 0.146%

    No Known Activations