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

    Neuronpedia

    INDEX
    Explanations

    sentences and phrases containing punctuation marks, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.83
     Theſe
    -0.73
    SourceChecksum
    -0.71
     насељу
    -0.68
    下载附件
    -0.68
    ']")
    -0.67
    \}\\
    -0.66
    "}")
    -0.66
     }}$}
    -0.65
    LookAnd
    -0.65
    POSITIVE LOGITS
    毕竟
    0.61
    畢竟
    0.57
     e
    0.52
     obě
    0.47
     perdana
    0.46
     but
    0.46
     SwitchCompat
    0.45
     noches
    0.45
    єра
    0.45
     even
    0.45
    Act Density 0.429%

    No Known Activations