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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and relational phrases that indicate connections or relationships between ideas

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

    list of qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.78
     Geſch
    -0.73
     houſe
    -0.72
     GenerationType
    -0.69
     ſche
    -0.68
     increí
    -0.68
    PreferredItem
    -0.67
     ſtate
    -0.66
     ſont
    -0.64
     quoque
    -0.64
    POSITIVE LOGITS
    完全
    0.34
    得
    0.34
    em
    0.32
     totally
    0.32
     verst
    0.32
    RelativeTo
    0.31
     highly
    0.31
     Bele
    0.31
    ig
    0.30
    lim
    0.30
    Act Density 0.032%

    No Known Activations