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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, specifically commas

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

    introduces new clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.55
     feroit
    -0.54
     AssemblyTitle
    -0.50
     légitime
    -0.45
    SequentialGroup
    -0.44
     inconn
    -0.44
     desconocido
    -0.43
     desierto
    -0.41
    engager
    -0.41
     réglable
    -0.41
    POSITIVE LOGITS
    adă
    0.65
     kasarigan
    0.57
    }{*}{
    0.56
    族館
    0.56
    brigens
    0.55
     Phry
    0.54
    сылкі
    0.54
    withIdentifier
    0.54
    __':
    0.53
    $_,
    0.52
    Act Density 0.069%

    No Known Activations