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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or text segment

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

    Follows a verb/noun usage

    np_acts-logits-general · gemini-2.0-flash

    took aside, when IMO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.58
     popular
    -0.58
     '/';
    -0.56
    popular
    -0.54
    oyant
    -0.53
    Auteur
    -0.52
    lamabad
    -0.52
    extField
    -0.52
    ślę
    -0.51
    });*/
    -0.50
    POSITIVE LOGITS
     refused
    0.69
     rudely
    0.65
    🤬
    0.65
     unprofessional
    0.64
     repeatedly
    0.64
    fjspx
    0.64
     supuestamente
    0.62
    Horrible
    0.61
     alleging
    0.60
     unilaterally
    0.60
    Act Density 0.155%

    No Known Activations