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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or specify examples or clarifications

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

    "namely" or its equivalents

    np_acts-logits-general · gemini-2.0-flash

    introducing an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fah
    -0.43
     flu
    -0.36
     pab
    -0.36
     صوتيه
    -0.35
    restrict
    -0.34
     ae
    -0.33
     Bened
    -0.33
    rens
    -0.33
     sympathetic
    -0.33
     Shenandoah
    -0.32
    POSITIVE LOGITS
     namely
    1.34
     Namely
    1.28
     nemlig
    1.24
    namely
    1.22
     nämlich
    1.02
     ovvero
    0.98
     yaitu
    0.97
     yakni
    0.96
     namelijk
    0.96
     iaitu
    0.94
    Act Density 0.703%

    No Known Activations