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

    Neuronpedia

    INDEX
    Explanations

    quotes and dialogue in the text

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

    Follows quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of quotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一方
    -0.62
    hile
    -0.53
     ενώ
    -0.53
    AndEndTag
    -0.51
    migrationBuilder
    -0.50
     etwa
    -0.50
    μών
    -0.50
    最快更新
    -0.49
     bowiem
    -0.48
    fromnode
    -0.48
    POSITIVE LOGITS
     it
    0.84
     noqa
    0.74
     obviously
    0.71
     everybody
    0.71
     Obviously
    0.70
     Hopefully
    0.69
     hopefully
    0.69
     приятно
    0.68
    principalColumn
    0.67
    Obviously
    0.67
    Act Density 0.080%

    No Known Activations