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

    Neuronpedia

    INDEX
    Explanations

    repetitive conjunctions and phrases suggesting addition or accumulation

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

    "and" followed by a determiner (the)

    np_acts-logits-general · gemini-2.0-flash

    linking clauses or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.98
     purpoſe
    -0.91
     Theſe
    -0.91
     Jefus
    -0.88
     becauſe
    -0.86
     fince
    -0.85
     houſe
    -0.83
     ſche
    -0.82
     ſtate
    -0.82
     pngtree
    -0.82
    POSITIVE LOGITS
     also
    0.83
     is
    0.57
     has
    0.55
     don
    0.51
     juga
    0.50
     
    0.50
     will
    0.48
     they
    0.48
     none
    0.47
    also
    0.47
    Act Density 0.043%

    No Known Activations