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

    Neuronpedia

    INDEX
    Explanations

    references to alternative situations or comparisons in a given context

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

    other than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.49
     increí
    -0.48
     Bewußt
    -0.44
     prêtres
    -0.43
    IsContent
    -0.42
    expandindo
    -0.42
    Cordialement
    -0.41
     vectorielle
    -0.40
    antaranya
    -0.40
     Escolar
    -0.40
    POSITIVE LOGITS
    nai
    0.46
    rrggbb
    0.45
     netizen
    0.44
    <?
    0.43
    nap
    0.43
    nacht
    0.42
     Mn
    0.42
    perman
    0.42
    skirts
    0.41
     Sauna
    0.41
    Act Density 0.235%

    No Known Activations