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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "discussed" or its context

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

    discussed in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.56
     maternity
    -0.44
    stunde
    -0.41
     bodyguard
    -0.40
     whoever
    -0.40
     desperation
    -0.39
    fw
    -0.39
     tuxedo
    -0.39
     IPS
    -0.39
     unwit
    -0.39
    POSITIVE LOGITS
     discussed
    1.41
    discussed
    1.26
    cussed
    1.03
     mentioned
    1.01
     talked
    0.98
     Mentioned
    0.96
    mentioned
    0.90
     described
    0.85
    described
    0.80
     Described
    0.77
    Act Density 0.012%

    No Known Activations