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

    Neuronpedia

    INDEX
    Explanations

    specific words or phrases that express confusion or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    why, なんで

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.47
     pestaña
    -0.47
    mtable
    -0.45
    fromnode
    -0.44
    บรร
    -0.43
    >{@
    -0.43
    AlterField
    -0.43
     embark
    -0.42
    findpost
    -0.41
    InputTagHelper
    -0.41
    POSITIVE LOGITS
     си
    1.77
    Си
    1.41
     Си
    1.34
    си
    1.16
    シ
    0.98
     СИ
    0.90
     Si
    0.85
    СИ
    0.84
     シ
    0.82
     Sy
    0.78
    Act Density 0.001%

    No Known Activations